CN202826324U - Monitoring device of module of injection molding machine - Google Patents
Monitoring device of module of injection molding machine Download PDFInfo
- Publication number
- CN202826324U CN202826324U CN 201220408581 CN201220408581U CN202826324U CN 202826324 U CN202826324 U CN 202826324U CN 201220408581 CN201220408581 CN 201220408581 CN 201220408581 U CN201220408581 U CN 201220408581U CN 202826324 U CN202826324 U CN 202826324U
- Authority
- CN
- China
- Prior art keywords
- core control
- module
- video image
- control panel
- image
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The utility model provides a monitoring device of a module of an injection molding machine. The monitoring device of the module of the injection molding machine comprises a digital signal processor (DSP) core control board, an infrared camera, an infrared source, a signal through connection board, a touch type liquid crystal display screen and a spare keyboard. The infrared camera, the touch type liquid crystal display screen, and the spare keyboard are all connected with the DSP core control board. The infrared source is located above a camera lens of the infrared camera. The injection molding machine is connected with the core control board through the signal through connection board. The DSP core control board adopts an overlap type framework, and a DSP minimum system board is connected with an external expansion board through an upper bus slot and a lower bus slot. The external expansion board comprises a video image input module, a video image output module and a storage administration module. The monitoring device of the module of the injection molding machine is small in size, convenient to operate and strong in commonality.
Description
Technical field
The utility model relates to injection machine industry in the industrial automatic control field, and especially a kind of injection machine mould monitoring arrangement is a kind of intelligentized mould protection equipment.
Background technology
Along with the continuous expansion of plastic products application, the whole world has presented lasting unprecedented soaring trend to the demand of injection machine in recent years.Carry out Real Time Monitoring to realize the automatic protection to mould for abnormal conditions such as residual, the slide block that mould in the injection machine production process is existed misplace, the demoulding is bad, the mould protector is introduced in the Injection Industry in a large number.This monitoring system based on image processing techniques has greatly improved security and the operating efficiency of injection mold, has reduced repair a die cost and staff's labour intensity.But also there are the shortcomings such as cost is higher, complicated operation, undetected, false drop rate is high in present mould protector, is mainly manifested in following two aspects.
Say from hardware point of view, existing mould protector general choice industrial computer is as main control unit, and industrial computer does not generally all have the Digital I/O interface, for the mutual control signal of injection machine, must the industrial computer of standard be transformed, increase the IO expansion interface; In addition, industrial computer does not have the analogue camera interface of standard yet, must increase image pick-up card or directly is connected with digital camera.Therefore, the whole system hardware cost is higher, and the system expandability is also relatively poor.
On the other hand; from the software angle, the mould protector function of introducing at present is all more single, and the image processing algorithm of mold protecting device inside is simple; intelligent degree is relatively low, the correctness that causes the complicated manually-operated of needs and experience to guarantee its result.For example, the sample learning before the operation, the empirical learning after reporting an error, the selection of multi-template, the artificial selection problem of surveyed area and some parameters etc.These all greatly depend on on-the-spot environment and operating personnel's experience.Simultaneously, the image deviations problem that playback is forbidden for mould, mechanical oscillation cause.The Zhan Changming of Xiamen University has adopted the template matching method of intensity-based to solve.But illumination variation can cause different gray scale attributes or contrast difference, so the Gray based matching algorithm often lacks robustness for illumination variation.The people such as the Mao Feng of Zhejiang University then utilize wavelet analysis method to solve the problem of geometrical deviation, and the impact by view data scatter diagram analyze and solve illumination variation is brought has obtained preferably effect, but the real-time of algorithm remains further to be improved.Because SIFT(Scale-invariant feature transform, yardstick invariant features conversion) feature has consistency to conversion such as the yardstick of image, illumination, translation, rotations.In recent years, many scholars are to studying based on the method for registering images of SIFT feature.The SIFT Feature Correspondence Algorithm is a kind of effective image matching algorithm that LoweD proposes, and the advantage of this algorithm is that the conversion such as the yardstick, illumination, translation, rotation to image has consistency, but also has the shortcoming of real-time deficiency.Therefore Sukthankar and Ke propose a kind of SIFT algorithm that uses principal component analysis; Bay has proposed the SURF algorithm---the SIFT algorithm of enhanced edition.SIFT algorithm real-time after these are optimized is better, but still is difficult to satisfy the requirement of real-time of mould protecting.The structure of image pyramid and too much key point are to cause one of not high major reason of algorithm real-time in the SIFT Feature Correspondence Algorithm.Therefore, this utility model adopts a kind of improved characteristics of image rapid registering algorithm: utilize FAST-9 Fast Corner Detection method improvement SIFT Feature Correspondence Algorithm.As another kind of enhancement mode SIFT Feature Correspondence Algorithm, it has solved the image deviations problem that illumination causes impact and on-the-spot noise, shade and the mechanical shock of characteristic matching efficiently, so that foreground image and background image can fit like a glove, also extremely meet the requirement of real-time of system.
Chinese patent also discloses the apparatus and method of some mould protections.As to authorize publication number be that the patent of invention of CN102152457A discloses a kind of embedded mould protective device based on Histogram Matching, judges whether to exist the goods of the not demoulding according to two histogrammic differences.This invention goes out the statistics variations of the significant edge of different images and color by histogrammic matching detection, reach the purpose of warning.But also there is following problem in this invention: after die sinking puts in place, before the manipulator crawl product, lack the one-time detection to product quality on the dynamic model; Illumination variation can cause different gray scale attributes or contrast difference, so the grey level histogram matching algorithm often lacks robustness for illumination variation.Authorizing for another example publication number is that the patent of invention of CN102363354A discloses a kind of injection machine mould protection system and method based on computer vision.Utilize infrared camera to judge whether product is qualified, again mould taken behind the blanking, judge whether the blanking success, and provide testing result.There is following problem equally in this invention: do not consider the impact of mechanical shock on detecting in the specification, lack crucial reasonably image processing algorithm and describe.The mandate publication number is that the patent of invention of CN102303397A discloses mold image monitoring method and the device that is used for die molding machine; this invention is compared the picture-storage of picked-up at interim storage element and with a large amount of benchmark images; judge; if there is erroneous judgement; this picture is added in the corresponding memory cell, finally reach the protective effect of mould.Equally also there is following problem in this invention: the image processing algorithm of mold protecting device inside is simple, and intelligent degree is relatively low, need to obtain a large amount of reference base picture by empirical learning, the correctness of guarantee testing result.And empirical learning greatly depends on on-the-spot environment and operating personnel's experience; Algorithm versatility and relatively poor to the robustness of environmental change; Along with the increase of samples pictures, the required time of the memory space that picture is required and detection algorithm all increases thereupon.
The utility model content
, complicated operation large for the volume that overcomes existing injection machine mould monitoring arrangement, the poor deficiency of versatility, the utility model provide a kind of volume, the injection machine mould monitoring arrangement that easy to operate, versatility is good of reducing.
The technical scheme that its technical problem that solves the utility model adopts is:
A kind of injection machine mould monitoring arrangement comprises DSP core control panel, thermal camera, infrared light supply and Signals Transfer Board; Described DSP core control panel adopts the superposing type framework, by two bus slots up and down DSP minimum system plate and external expanding plate are connected, described external expanding plate comprises video image input module, video image output module and memory management module, described thermal camera links to each other with the video image input module of core control panel by camera interface, infrared light supply is positioned at the camera lens top of described thermal camera, and described Signals Transfer Board links to each other injection machine with core control panel.
Further, described video image input module adopts TVP5150 chip design decoding circuit, described video image output module is supported CVBS and two kinds of analog signal outputs of VGA, and described memory management module is that 32 EMIF buses are expanded the DDR2 SDRAM of 256M bytes and by the FLASH of EMIFA Interface Expanding 4M byte.
Further again, described monitoring arrangement also comprises touch liquid crystal display and keyboard for subsequent use, and described touch liquid crystal display links to each other with the video image output module of core control panel by interface; Keyboard for subsequent use is connected with the DSP core control panel.
The input side of described Signals Transfer Board is isolated by photoelectricity, and the outlet side of described Signals Transfer Board is isolated by relay.
The result of described monitoring arrangement shows the interactive man-machine interface of employing, and described interactive man-machine interface comprises interface menu and status bar: interface menu comprises the options such as surveyed area selection, parameter setting, systematic learning and touch-screen correction; Status bar is display system status information then, comprises the status informations such as warning, I/O mouth and Riming time of algorithm.
The beneficial effects of the utility model are mainly manifested in: modularized design, and it is convenient to install, and can directly plug; Can set the surveyed area of arbitrary shape, applicable various complicated dies, highly versatile.Core control panel adopts the superposing type framework, by two bus slots up and down minimum system plate and external expanding plate is connected, and reduces system bulk; The minimum system plate adopts dsp processor at a high speed, and the determination processing time is no more than 0.3 second; And abundant input and output IO interface is provided, by Signals Transfer Board finish and injection machine between level conversion; Infrared light supply cooperates thermal camera, can reduce on-the-spot illumination to the interference of system; Interactive man-machine interface, objective interface shows human nature, and is simple to operate, and the common laborer without specific (special) requirements, also be need not long-time study.Store or Real Time Monitoring by remote host through outputing to by the 10/100M Ethernet interface behind the compressed encoding for the video image of output; Extend out DDR2 SDRAM and FLASH and can store great amount of images data and run time version.The CVBS of standard and VGA output interface, highly versatile.
Description of drawings
Fig. 1 is the block architecture diagram of injection machine mould monitoring arrangement.
Fig. 2 is the theory diagram of DSP core control panel.
Fig. 3 is based on the rapid registering algorithm flow chart of FAST-9 characteristics of image.
Fig. 4 is the schematic diagram of rapid image feature point extraction.
Fig. 5 is based on the flow chart of the mould supervision method of FAST-9 characteristics of image rapid registering algorithm.
The specific embodiment
Below in conjunction with accompanying drawing the utility model is further described.
With reference to Fig. 1～Fig. 5, a kind of injection machine mould monitoring arrangement, its hardware structure are divided into five parts as shown in Figure 1: DSP core control panel, thermal camera, infrared light supply, Signals Transfer Board, touch liquid crystal display and keyboard for subsequent use.
The DSP core control panel is the main body of hardware platform, and as shown in Figure 2, control panel adopts the superposing type framework, by two bus slots up and down DSP minimum system plate and external expanding plate is connected, to reduce system bulk.DSP minimum system plate is the elementary cell that starts microprocessor; External expanding plate comprises video image input module, video image output module and memory management module.The video image input module adopts TVP5150 chip design decoding circuit, the video image stream of 25 frame/seconds of standard is converted into the vedio data of 8 ITU-R BT.656 form; The video image output module is supported CVBS and two kinds of analog signal outputs of VGA, and the video image of output also can remote host be stored or further processing through outputing to by the 10/100M Ethernet interface behind the compression algorithm coding; In memory management module, system is by the DDR2 SDRAM of 32 EMIF bus expansion 256M bytes, and the while is by the FLASH of EMIFA Interface Expanding 4M byte, in order to storing image data and run time version.Signals Transfer Board is finished the level conversion of signal input and output between injection machine and the DSP core control panel.Infrared light supply cooperates thermal camera, can significantly reduce extraneous illumination variation to the impact of system; Interactive man-machine interface is then in conjunction with the OSD(OSD of DSP Video processing rear end (VPBE), On-Screen Display) window management, and according to the GUI principle of stratification (gui interface is divided into hardware driving layer, basic figure layer, the advanced interface layer) designing user operation interface.Interface menu comprises the options such as surveyed area selection, parameter setting, systematic learning and touch-screen correction, and status bar is display system status information then, comprises the status informations such as warning, I/O mouth and Riming time of algorithm.
In order to solve illumination the impact of characteristic matching and on-the-spot noise, shade and mechanical shock are caused geometrical offset problem between photo site and the template picture, so that foreground image and background image can fit like a glove, this utility model adopts a kind of based on FAST-9 characteristics of image rapid registering algorithm: utilize FAST-9 Fast Corner Detection method improvement SIFT Feature Correspondence Algorithm.As another kind of enhancement mode SIFT algorithm, greatly strengthened the real-time of system, satisfy the designing requirement of system.Idiographic flow such as Fig. 3.
The DSP core control panel is the main body of hardware platform, adopts the superposing type framework, by two bus slots up and down DSP minimum system plate and external expanding plate is connected, to reduce system bulk.DSP minimum system plate is the elementary cell that starts microprocessor; External expanding plate comprises video image input module, video image output module and memory management module.
The video image input module, native system adopts TVP5150 chip design decoding circuit, it is converted into the input video stream of simulation the digital video image data of 8 ITU-R BT.656 form, dsp processor deposits the BT.656 data flow in FIFO by the video port on the sheet, then move into the data among the FIFO in the sheet or chip external memory by the EDMA passage, in program, can call view data and process.Also can gather the subregion in the video image by the video port register is set, carry out image cropping.
The video image output module is supported CVBS and two kinds of analog signal outputs of VGA, and one road DAC is as voltage reference lines and the output of R deviation signal; Three road DAC_A, DAC_B, DAC_C are as the output of VGA pattern in addition, and DAC_A also exports as the CVBS mode multiplexing simultaneously.The video image of output also can be through outputing to by the 10/100M Ethernet interface that remote host is stored behind the compression algorithm coding or further processing.
Memory management module, system is by the DDR2 SDRAM of 32 EMIF bus expansion 256M bytes, and the while is by the FLASH of EMIFA Interface Expanding 4M byte, in order to storing image data and run time version.
Signals Transfer Board is finished the level conversion of signal input and output between injection machine and the DSP core control panel.Input is isolated by photoelectricity, reduces the interference that controller of plastic injection molding brings, and output has increased the driving force of signal simultaneously by the relay isolation.
Infrared light supply cooperates thermal camera, can avoid the impact of other visible lights, thereby obtain the image of best results.Common industrial camera then easily is subjected to illumination variation to the interference of system.
Interactive man-machine interface is then in conjunction with the OSD window management of DSP Video processing rear end (VPBE), and according to GUI principle of stratification designing user operation interface.Interface menu comprises the options such as surveyed area selection, parameter setting, systematic learning and touch-screen correction, and status bar is display system status information then, comprises the status informations such as warning, I/O mouth and Riming time of algorithm.
In above each unit, video camera links to each other with the video image input module of core control panel by camera interface, gathers image information.Touch liquid crystal display links to each other with the video image output module of core control panel by interface, shows final result.Injection machine links to each other with core control panel by Signals Transfer Board.
System Working Principle is as follows: at a complete mould molding in the cycle, when injection machine moves to die sinking and puts in place, output signal triggers the mould monitoring system, system by video camera to the continuous capture of die cavity, gather via Signals Transfer Board simultaneously that die sinking puts in place, the injection machine duties such as thimble puts in place, safety door, and then by the DSP core control panel monitoring image is analyzed and processed, eliminate because the impact that the factors such as on-the-spot noise, light, shade and mechanical oscillation cause.Incomplete by relatively determining whether there is shaped article, if any unusually then warning, otherwise continue.After the injection machine thimble ejects, again gather image, whether the monitoring thimble ejects shaping workpiece and falls, when monitor workpiece fall fully then send allow signal feedback to injection machine with the beginning next cycle; As workpiece in setting-up time not yet fall or mould between when foreign material are arranged, then send abnormal signal, stop the injection machine action and report to the police.Meanwhile, whenever in a single day the DSP core control panel detects unusual safety door signal in the above process, stops immediately injection machine action and warning.The parameter setting of system, alarm state information and Real Time Monitoring picture are then provided by touch liquid crystal display.
In cycle, the conduct of injection machine mould monitoring arrangement is workbench independently at a complete mould molding, can provide accurate testing result to an inspection and two inspections under intelligentized duty.
Monitor that based on the mould of FAST-9 characteristics of image rapid registering algorithm method flow diagram is described in further details the realization of this injection machine mould device in conjunction with Fig. 5 below by a production instance:
Step 1: when gathering respectively injection moulding machine mould open and putting in place and the standard form image of thimble after ejecting, and carry out preliminary treatment, the information with irrelevant in the removal of images finally is stored in the memory module of DSP core control panel; Wait for that die sinking puts in place, the injection machine work state informations such as thimble puts in place, safety door; System is in monitoring during workpiece, to the continuous capture of mold cavity face, and by the DSP core control panel present frame of monitoring image is done preliminary treatment by video camera, for follow-up Rapid Image Registration is prepared; Carry out afterwards based on FAST-9 characteristics of image rapid registering algorithm, make the rapid registering of doing characteristics of image between present frame and the template image, eliminate because the impact that the factors such as on-the-spot noise, light, shade and mechanical shock cause; Again present frame and template image after the registration are done difference; Adopt Ostu automatic threshold segmentation algorithm to realize image binaryzation; Image is carried out continuous open and close computing to eliminate influence of noise; At last by air cavity detection check whether exist unusual, if having unusually then in the touch-screen display alarm information, injection machine stops pressing mold and enters the interlock protection measure; Otherwise continue to wait for that die sinking puts in place, the injection machine work state informations such as thimble puts in place, safety door.
Step 2: after the injection machine thimble ejects, to the continuous capture of mold cavity face, and by the DSP core control panel present frame of monitoring image is done preliminary treatment by video camera, for follow-up Rapid Image Registration is prepared; Carry out afterwards based on FAST-9 characteristics of image rapid registering algorithm, make the rapid registering of doing characteristics of image between present frame and the template image, eliminate because the impact that the factors such as on-the-spot noise, light, shade and mechanical shock cause; Again present frame and template image after the registration are done difference; Adopt Ostu automatic threshold segmentation algorithm to realize image binaryzation; Image is carried out continuous open and close computing to eliminate influence of noise; Whether shaping workpiece is ejected by air cavity detection monitoring thimble at last and fall, allow signal feedback to injection machine, to begin the waiting for next mould molding cycle when workpiece falls to then sending fully; As workpiece in setting-up time not yet fall or mould between when foreign material are arranged, then injection machine stops matched moulds and in the touch-screen display alarm information.In the above process in any case the DSP core control panel in a single day detect unusual safety door signal, stop immediately injection machine action and report to the police.
Below by a production instance to being described in further detail based on FAST-9 characteristics of image rapid registering algorithm:
Step 1: utilize FAST-9 Fast Corner Detection method to obtain respectively realtime graphic and sample image key point, the pixel value of continuous 9 points thinks then that all than high or low 50 gray values of current center of circle P this point is exactly key point (such as Fig. 4) on gloomy Durham circle.
Step 2: according to the gradient magnitude of key point neighborhood territory pixel, the principal direction that Direction Distribution Characteristics is determined key point, choose simultaneously amplitude up to the energy peak of main peak 80% as auxiliary direction.
Step 3: face area image with 16 * 16 and rotate to principal direction consistent with the image X-direction, and this is faced the territory be divided into 4 * 4 sub regions, and calculate the histogram of gradients of 8 directions in 4 * 4 subregions, 4 * 4 * 8 totally 128 dimension descriptor L=(l of final generating standard
1, l
2... l
128).
Step 4: characteristic matching: when the ratio of the arest neighbors of characteristic vector Euclidean distance and time nearest neighbor distance less than 0.6 the time, think that then the match is successful.
Step 5: mismatch a little with the rejecting of RANSAC method, obtain actual model parameter
If characteristic point p is (x
1, y
1) and q (x
2, y
2) be the characteristic point pair of coupling, transformation relation is then arranged:
Characteristics of image rapid registering algorithm steps according to foregoing description obtains proofreading and correct rear image: the matching result of characteristic point is indicated with line.Test shows: this algorithm is in the situation that image quality is not high or illumination effect has all been obtained better matching effect.
In addition, choose the mould picture of one group of unknown geometrical deviation.Provide simultaneously the differential effect comparison diagram of the mold image registration front and back that have foreign matter, and carried out binary conversion treatment, finally realized simple mould surveillance foreign matter measuring ability.Test shows: do not pass through image registration, a large amount of false targets that detect occurred, difference image is brought obvious interference, even affect testing result.And the correction of process characteristics of image rapid registering algorithm, small deviation just appears between image, thereby efficiently solve the interference that image shift causes, testing result is desirable, tally with the actual situation, illustrate that this algorithm can effectively solve the image geometry offset issue in the mould surveillance, reduced greatly mould loss and false drop rate, more obviously embodied the superiority of this utility model.
Claims (4)
1. injection machine mould monitoring arrangement, it is characterized in that: described monitoring arrangement comprises DSP core control panel, thermal camera, infrared light supply and Signals Transfer Board, described DSP core control panel adopts the superposing type framework, by two bus slots up and down DSP minimum system plate and external expanding plate are connected, described external expanding plate comprises video image input module, video image output module and memory management module; Described thermal camera links to each other with the video image input module of core control panel by camera interface, and infrared light supply is positioned at the camera lens top of described thermal camera, and described Signals Transfer Board links to each other injection machine with core control panel.
2. injection machine mould monitoring arrangement as claimed in claim 1, it is characterized in that: described video image input module adopts TVP5150 chip design decoding circuit, described video image output module is supported CVBS and two kinds of analog signal outputs of VGA, and described memory management module is that 32 EMIF buses are expanded the DDR2SDRAM of 256M bytes and by the FLASH of EMIFA Interface Expanding 4M byte.
3. injection machine mould monitoring arrangement as claimed in claim 1, it is characterized in that: described monitoring arrangement also comprises touch liquid crystal display and keyboard for subsequent use, described touch liquid crystal display links to each other with the video image output module of core control panel by interface; Keyboard for subsequent use is connected with the DSP core control panel.
4. injection machine mould monitoring arrangement as claimed in claim 1 or 2, it is characterized in that: the input side of described Signals Transfer Board is isolated by photoelectricity, and the outlet side of described Signals Transfer Board is isolated by relay.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201220408581 CN202826324U (en) | 2012-08-17 | 2012-08-17 | Monitoring device of module of injection molding machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201220408581 CN202826324U (en) | 2012-08-17 | 2012-08-17 | Monitoring device of module of injection molding machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202826324U true CN202826324U (en) | 2013-03-27 |
Family
ID=47938110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201220408581 Expired - Fee Related CN202826324U (en) | 2012-08-17 | 2012-08-17 | Monitoring device of module of injection molding machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202826324U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105619741A (en) * | 2016-03-28 | 2016-06-01 | 浙江工业大学 | Tegra K1-based intelligent detection method for die |
| CN109435204A (en) * | 2018-10-23 | 2019-03-08 | 河北三能科技有限公司 | It is a kind of for controlling the cruise constant speed control system and method for Rubber Extruder |
| CN113276373A (en) * | 2021-06-06 | 2021-08-20 | 高萍 | Wine set molding machine anomaly detection system |
-
2012
- 2012-08-17 CN CN 201220408581 patent/CN202826324U/en not_active Expired - Fee Related
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105619741A (en) * | 2016-03-28 | 2016-06-01 | 浙江工业大学 | Tegra K1-based intelligent detection method for die |
| CN105619741B (en) * | 2016-03-28 | 2018-01-23 | 浙江工业大学 | A kind of mould intelligent detecting method based on Tegra K1 |
| CN109435204A (en) * | 2018-10-23 | 2019-03-08 | 河北三能科技有限公司 | It is a kind of for controlling the cruise constant speed control system and method for Rubber Extruder |
| CN113276373A (en) * | 2021-06-06 | 2021-08-20 | 高萍 | Wine set molding machine anomaly detection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102837406B (en) | Mold monitoring method based on FAST-9 image characteristic rapid registration algorithm | |
| CN104441526B (en) | Mould in-service monitoring protection system and method based on appearance profile coupling | |
| CN101477631B (en) | Method, equipment for extracting target from image and human-machine interaction system | |
| CN105701476A (en) | Machine vision-based automatic identification system and method for production line products | |
| CN102706274B (en) | System for accurately positioning mechanical part by machine vision in industrially-structured scene | |
| CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
| CN202826324U (en) | Monitoring device of module of injection molding machine | |
| CN203629603U (en) | Intelligent electric energy meter detection device based on image identification technology | |
| CN103552224B (en) | Injection compression molding optical-grade transparent quality of item online test method | |
| CN101464751B (en) | Electronic white board system based on image detection and detection method thereof | |
| CN106483143A (en) | A kind of solar energy photovoltaic panel dust stratification on-Line Monitor Device and its detection method | |
| CN109596631B (en) | Cigarette packet seal wrong-brand detection device and method based on machine vision technology | |
| CN102152457B (en) | Embedded plastic mould protector based on histogram matching | |
| CN105619741A (en) | Tegra K1-based intelligent detection method for die | |
| CN204546978U (en) | Based on the injection machine mould monitoring arrangement of ARM | |
| CN103945124A (en) | Control method for intelligent camera | |
| CN113469938A (en) | Pipe gallery video analysis method and system based on embedded front-end processing server | |
| CN202029367U (en) | Embedded plastic mould protecting device based on histogram matching | |
| CN111231253A (en) | Injection molding safety production system based on machine vision | |
| CN109975312A (en) | A kind of cigarette bobbin paper quality detection device and method based on machine vision technique | |
| CN208155893U (en) | binocular vision scratch detection system based on high speed camera | |
| CN103618899A (en) | Video frame interpolation detecting method and device based on light intensity information | |
| CN116253026A (en) | Cigarette appearance detection and discrimination processing system and method for GDX2 packaging equipment | |
| CN204718551U (en) | A kind of automated production checkout equipment | |
| Lin et al. | One-shot learning gesture recognition based on improved 3D SMoSIFT feature descriptor from RGB-D videos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130327 Termination date: 20150817 |
|
| EXPY | Termination of patent right or utility model |