CN105930854A - Manipulator visual system - Google Patents
Manipulator visual system Download PDFInfo
- Publication number
- CN105930854A CN105930854A CN201610244119.2A CN201610244119A CN105930854A CN 105930854 A CN105930854 A CN 105930854A CN 201610244119 A CN201610244119 A CN 201610244119A CN 105930854 A CN105930854 A CN 105930854A
- Authority
- CN
- China
- Prior art keywords
- image
- visual system
- mechanical arm
- module
- carries out
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a manipulator visual system. The model of a whole visual system is established based on the visual assistant of Labview. The system comprises an image acquisition module for acquiring an image in a manipulator operating platform, a pre-processing module for carrying out enhancing, smoothing and denoising processing on the obtained image, a segmentation module for removing unnecessary information in the image, and an identification module for carrying out characteristic extraction on the image with the removal of the unnecessary information to realize the identification of geometry color and shape. The system can effectively identify an object, the labor cost is reduced, and the working efficiency is improved.
Description
Technical field
The present invention relates to technical field of robot vision, particularly relate to a kind of mechanical arm visual system.
Background technology
Along with image procossing, pattern recognition, the development of intelligent control technology with reach its maturity, intelligent machine man-based development and should
Being used in recent decades and achieve significant progress and the extensive concern of numerous experts and scholars, the research of machine vision simultaneously is the most
Move towards actual application from laboratory, develop into the image procossing of the many gray scales of high-resolution from simple binary Images Processing；From one
As two-dimensional signal process develop into 3D vision process, the research of corresponding algorithm also achieves bigger progress, widely
It is applied in the field such as vision-based detection and Automated assembly.The most increasing occasion uses the operation of robot, particularly
Work that some heavy, repeated strong or hazardous environments perform, undoubtedly, robot will be in coming few decades
Playing the part of prior role in commercial production, human lives, the productive life for people brings huge facility and help.For
Improve adaptation and the learning capacity of robot, robot have to from complex environment self-obtaining information, and to possess
This ability is necessary for relying on various kinds of sensors, such as touch sensor, range sensor, vision sensor etc., the heaviest
Want no more than vision sensor, just as the eyes of people, the external information more than 90% acquired in the mankind is all by eye
Eyeball obtains, and this has absolutely proved the importance of vision, also illustrate that what vision contained contains much information, and utilization rate is high.Research
Find that the robot with visual system can save a large amount of labour force in the application of logistics sort process, save the plenty of time, fall
Low labour cost, improves work efficiency, reduces security incident, significant to enterprise development, and enterprise warp also can be greatly improved
Ji benefit.
Summary of the invention
The technical problem to be solved is to provide a kind of mechanical arm visual system, it is possible to effectively identify object,
Reduce human cost, improve work efficiency.
The technical solution adopted for the present invention to solve the technical problems is: provide a kind of mechanical arm visual system, based on Labview
Visual aids establish the model of whole visual system, including image collection module, be used for obtaining robotic arm manipulation platform
On image；Pretreatment module, for strengthening the image obtained, smoothing and denoising；Segmentation module, is used for
Remove information unnecessary in image；Identification module, for remove unnecessary information image carry out feature extraction realize right
The identification of solid CF.
Described pretreatment module uses Sober operator that the image obtained is carried out rim detection and realizes smoothing processing.
Described pretreatment module uses fourier filter that the image obtained is carried out denoising.
Described pretreatment module uses the binary conversion treatment of adaptive threshold that the image obtained is carried out enhancement process.
Described identification module carries out sampling analysis to the color of image, when the RGB component of color of image mates with template colors
Shi Ze identifies the color of image.
Described identification module uses the mode of polygon sample train template matching to realize the identification to polygon image, uses circle
Shape detection function realizes the identification to circular image.
Beneficial effect
Owing to have employed above-mentioned technical scheme, the present invention compared with prior art, has the following advantages that and good effect:
The present invention utilizes video camera to shoot photo, and photo is carried out relevant treatment, accurately realizes the identification to solid CF,
And coarse localization solid center position, utilize vision software NI VisionAssistant based on American National instrument NI
Realize image processing and analyzing and feature extraction and location, human cost can not only be reduced, more can improve work efficiency, the most also
More benefit can be brought.
Accompanying drawing explanation
Fig. 1 is the functional-block diagram of the present invention.
Detailed description of the invention
Below in conjunction with specific embodiment, the present invention is expanded on further.Should be understood that these embodiments be merely to illustrate the present invention and
It is not used in restriction the scope of the present invention.In addition, it is to be understood that after having read the content that the present invention lectures, people in the art
The present invention can be made various changes or modifications by member, and these equivalent form of values fall within the application appended claims equally and limited
Scope.
Embodiments of the present invention relate to a kind of mechanical arm visual system, and visual aids based on Labview establishes whole regarding
The model of vision system, as it is shown in figure 1, include: image collection module, for obtaining the image on robotic arm manipulation platform；
Pretreatment module, for strengthening the image obtained, smoothing and denoising；Segmentation module, is used for removing in image
Unnecessary information；Identification module, realizes solid color for the image removing unnecessary information carries out feature extraction
Identification with shape.
The principle of the present invention is:
(1) utilize Python programming language realize video camera is called, the picture on camera mechanical arm operating platform for
Subsequent treatment.
(2) NI VisionAssistant software is utilized to realize analysis, process, feature extraction and the location to picture.
The present invention is as a example by Tripod robot sort process, and machine vision replaces human eye measure and judge with machine exactly,
Obtained the two dimensional image of target object by the vision sensor being equipped with, by processor, the two dimensional image obtained is entered simultaneously
Row is analyzed and is processed, and draws useful information, and then is converted into control signal, and driven machine people takes to operate accordingly, this
It is possible not only to improve the automaticity of production line, it may also be used in high volume in industrial processes.For meeting Tripod machine
People in real time, online, accurately captures requirement, to the imagery exploitation edge extracting gathered, filtering and noise reduction and center of circle detection scheduling algorithm,
Use and carry out the pretreatment of image and feature extraction based on LabVIEW2014 and vision module (VDM) and central point is fixed
Bit manipulation, has reached good effect.A kind of general program that LabVIEW develops as American National instrument (NI) company
Development environment, has that simple in construction, function be strong, precision high, application IMAQ Vision image procossing kit and
NI VisionAssistant, highly shortened the construction cycle.
Machinery and the motion control portion of this Tripod robot are provided by Bei Jialai company (B&R), and robot is added by shellfish
Lay equipment is driven, including three shaft mechanical arms, ACOPOS servomotor, decelerator, X20 Series Controller and switch
Power supply, the device such as PLC, camera is the requisite building block of Vision Builder for Automated Inspection in addition, main point of CCD and CMOS
Two kinds, the former processing technology is relative complex, relatively costly, and image quality is good；The latter is more weak to color restoration capability, penetrating
Property general, but power consumption is few, low cost, it is contemplated that image quality, in present embodiment, image collection module selects CCD
Camera, is arranged on operating platform top, carries out image taking and collection, and camera imaging is easily subject to environment and brightness impact,
In order to obtain image the most clearly, it is also considered that the inconvenience in the process that brightness of image problem is brought, by operating platform
Placement light is illuminated, and reduces the too dark impact on image effect of light.
The major part work of Tripod robotic vision system is the identification of early stage characteristics of image, accurate position feature ability
Reach stable control effect.Vision robot's system block diagram based on image, mainly by camera acquisition image, image
Reason software extracts position feature information after processing, and acts on vision controller with desired character after comparing, thus
Control robot motion.
LabVIEW (laboratory virtual instrument work platforms) is that a kind of general program that American National instrument (NI) company develops is opened
The system of sending out, is one and uses graphical symbol to use the programmed environment that G language is write, can be operated in operation Windows,
Mac, on the computer of linux system, it is also possible to operate on the embedded platform including including FPGA, DSP etc..Make
Being divided into front panel and two parts of flow chart with LabVIEW, front panel shows for input and output, and flow chart completes
Corresponding program connects, and is effectively simplified program development, adds the intuitive of program, highly shortened the construction cycle.
LabVIEW visual development module includes that IMAQ Vision and NI VisionAssistant, IMAQ Vision are LabVIEW
Visual development tool kit, it contains the function library that more than 400 kind of machine vision and scientific imagery process, in conjunction with LabVIEW
The integrated performance of good software and hardware and the high efficiency of graphic language, it is possible to realize the related application of view-based access control model in each field；NI
VisionAssistant is an interactively development environment, it is not necessary to complicated programming, can set up the mould of vision utility system
Type.Native system uses and realizes specific merit based on the NI VisionAssistant on this platform and IMAQ Vision collaborative work
Can, comprise image procossing and feature identification overall process.Due to funds and the restriction of hardware, do not use the image pick-up card of specialty
Gather image, but utilize software programming to achieve corresponding acquisition function, use SimpleCV based on Python
Programming tool, Python grammer is simple, readable strong, and programming realization is clicked on left button and controlled camera shooting picture and be saved in phase
Answer position, call for NI VisionAssistant
In most cases, due to experimental system and the restriction of filming apparatus, the image of acquisition mostly contain a lot of noises and
Distortion, cannot be directly used in visual system in the case of the most preprocessed, and it is necessary for therefore image being carried out pretreatment,
By the pretreatment of image, some noises can be filtered out and make the factor of image deterioration, strengthening the information of target object simultaneously,
Image is made to be more prone to process and analyze, advantageously in the extraction of target object feature.Present embodiment uses NI public
The LabVIEW software of department combines visual aids and can be good at realizing the process to image and feature extraction.
Described pretreatment module uses Sober operator that the image obtained is carried out rim detection and realizes smoothing processing, uses in Fu
Leaf wave filter carries out denoising to the image obtained, and uses the binary conversion treatment of adaptive threshold to increase the image obtained
Strength is managed.Specific as follows:
The edge feature of image is the feature that piece image is most basic, and edge extracting i.e. extracts the edge contour of target image, uses
Detection and analysis in feature.Conventional edge detection operator has Canny, Laplacian and Sober operator etc., this enforcement
Mode uses Sober operator and carries out rim detection, and this operator comprises the matrix of horizontal and vertical two groups of 3x3, by it with
Image makees planar convolution, can draw the brightness difference approximation of transverse direction and longitudinal direction respectively, owing to doing the impact of location of pixels
Weighting, this operator can effectively reduce edge blurry degree, be suitable at the image more to gray scale gradual change and noise
Reason, has certain smoothing effect to noise, and affected by noise less, however, in addition it is also necessary to utilize Fourier filtering
Device eliminates noise, utilizes Fourier transformation to obtain signal spectrum, removes unwanted portions of the spectrum as required and reaches filter
The effect of ripple, to obtain more smooth, sharp-pointed edge contour.
The binaryzation of image is the necessary links of image procossing, and binary image can increase the contrast of image, strengthens image
Effect, accelerates recognition efficiency, and binaryzation it is critical only that asking for of threshold value, suitable threshold value to the process of image to closing weight
, threshold value obtains mainly global threshold and two kinds of methods of adaptive threshold, and global threshold is that entire image only uses one
Threshold value T does the segmentation of image, and this method is adapted to background and the obvious simple image of foreground separation；Adaptive threshold is
Different threshold values can be used to split different characteristic region in image, it is adaptable to complex object and background contrasts are not united
The image of one.In present embodiment, the acquisition of threshold value uses adaptation metrics method, simultaneously in order to more be smoothed, clearly
Image, it is also possible to image is smoothed again, eliminates further the noise impact on picture quality, select intermediate value filter
Ripple processes, and medium filtering is by non-linear being averaged of gray value in a certain pixel field is replaced this pixel
Gray value, can overcome the fuzzy of the image that linear filtering brings to a certain extent.Due to particle each in binary image
Or region all has an impact on single basal morphological, for the ease of follow-up quantitative analysis, need to carry out as expansion, fill,
Reduce target, close the work such as particle, smooth boundary, the method selecting corrosion target (Erode objects) here,
Inverting binary image afterwards, making background pixel is particle, and particle is that background pixel completes Image semantic classification.
Described identification module carries out sampling analysis to the color of image, when the RGB component of color of image mates with template colors
Shi Ze identifies the color of image.Described identification module uses the mode of polygon sample train template matching to realize polygon
The identification of image, uses circle detection function to realize the identification to circular image.
The motor control of mechanical arm needs to receive solid positional information, therefore needs operation after completing Image semantic classification
On platform, solid feature is identified and explains, operating platform has triangle, pentagon, circular three kinds of different shapes
And yellow, orange, blue three kinds of different colors, colour recognition may utilize the pixel value RGB component of color and mates, RGB
Three-component value constitutes three-dimensional array, and wherein, orange R component value is higher, and blue B component value is higher, and yellow R and G divide
Value is higher.Respectively yellow, orange, blue three-color are carried out sampling analysis during identification, just can realize the division of solid color.
As a example by identifying yellow, first create the sample template of a yellow, analyze the RGB component of this color, sensitivity is set
Deng, mate as template, arranging smallest match mark is 800 points, and when less than 800, then it fails to match, and display " is lost
Lose ", on the contrary display " successfully ".
Triangle, pentagonal identification use form fit function to mate, and principle is all that sample train template is identified.
As a example by triangle identification, first choose in picture and create a triangle template, it is ensured that the template edge profile chosen
Clearly, set smallest match mark as 900, identify that the mark triangle more than 900 all can be labeled and records center point
Pixel coordinate information.
Circular to know method for distinguishing a lot, traditional are widely used such as Hough loop truss algorithm, but not directly easy,
Present embodiment directly utilizes the circle detection function that NI visual aids carries and mates, and arranges corresponding radius interval,
Can identify corresponding circular fast and accurately, utilize minimum two-multiply law to carry out center of circle detection and can reach error sum of squares minimum
Fitting effect, when being positioned on a circumference, the position in the center of circle, i.e. " three-point circle method " can be determined by parsing at 3；
When counting more than 3 of collection point, can carry out curve fitting with method of least square, try to achieve round position, determine that the center of circle is sat
Mark.
It is seen that, the present invention establishes the model of whole visual system by visual aids based on Labview, utilizes
Sober operator carries out edge extracting, and adaptive threshold carries out binaryzation, Fourier filtering and median smoothing denoising and completes image
Pretreatment, sampling triangle, pentagon template mate, circle detection and solid location of the core etc., and success is real
Show yellow, orange, the detection of blue three-color and triangle, pentagon and the identification of circular three kinds of shapes, and extracted
It is easy to the positional information of subsequent control.Traditional manpower that utilizes carries out the time-consuming effort of object sorting work, and the present invention is object
Sorting work brings a kind of preferably executive mode, by Machine Vision Recognition object, extracts useful information, then controls
Mechanical arm operates, and can not only reduce human cost, more can improve work efficiency, also bring along more benefit simultaneously,
This Tripod robot system based on machine vision can be brought huge for the productive life of the commercial production even mankind undoubtedly
Facility, have broad application prospects and use value.
Claims (6)
1. a mechanical arm visual system, it is characterised in that visual aids based on Labview establishes whole visual system
Model, including: image collection module, for obtaining the image on robotic arm manipulation platform；Pretreatment module, is used for
The image obtained is strengthened, smooths and denoising；Segmentation module, for removing information unnecessary in image；
Identification module, realizes the knowledge to solid CF for the image removing unnecessary information carries out feature extraction
Not.
Mechanical arm visual system the most according to claim 1, it is characterised in that described pretreatment module uses Sober to calculate
Son carries out rim detection to the image obtained and realizes smoothing processing.
Mechanical arm visual system the most according to claim 1, it is characterised in that described pretreatment module uses Fourier's filter
Ripple device carries out denoising to the image obtained.
Mechanical arm visual system the most according to claim 1, it is characterised in that described pretreatment module uses adaptive thresholding
The binary conversion treatment of value carries out enhancement process to the image obtained.
Mechanical arm visual system the most according to claim 1, it is characterised in that the color of image is entered by described identification module
Row sampling analysis, then identifies the color of image with template colors when the RGB component of color of image mates.
Mechanical arm visual system the most according to claim 1, it is characterised in that described identification module uses polygon sampling
The mode of training template matching realizes the identification to polygon image, uses circle detection function to realize circular image
Identify.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610244119.2A CN105930854A (en) | 2016-04-19 | 2016-04-19 | Manipulator visual system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610244119.2A CN105930854A (en) | 2016-04-19 | 2016-04-19 | Manipulator visual system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105930854A true CN105930854A (en) | 2016-09-07 |
Family
ID=56838446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610244119.2A Pending CN105930854A (en) | 2016-04-19 | 2016-04-19 | Manipulator visual system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105930854A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106636510A (en) * | 2016-10-20 | 2017-05-10 | 三峡大学 | Automatic brazing rod changing method based on machine vision |
| CN106846342A (en) * | 2017-02-23 | 2017-06-13 | 东莞市旭海机械有限公司 | A kind of Full-automatic tobacco bag cutting machine |
| CN107272569A (en) * | 2017-08-11 | 2017-10-20 | 重庆邮电大学 | A kind of long-range motion control experimental facility |
| CN108109174A (en) * | 2017-12-13 | 2018-06-01 | 上海电气集团股份有限公司 | A kind of robot monocular bootstrap technique sorted at random for part at random and system |
| CN108405374A (en) * | 2018-02-01 | 2018-08-17 | 上海建桥学院 | A kind of mechanical arm picking up system of automatic discrimination different colours |
| CN108480223A (en) * | 2018-03-19 | 2018-09-04 | 厦门理工学院 | A kind of workpiece sorting system and its control method |
| CN108964361A (en) * | 2018-07-14 | 2018-12-07 | 芜湖益浩昌智能设备有限公司 | A kind of driving control system for servo motor |
| CN108959998A (en) * | 2018-06-25 | 2018-12-07 | 天津英创汇智汽车技术有限公司 | Two-dimensional code identification method, apparatus and system |
| CN109191693A (en) * | 2018-07-23 | 2019-01-11 | 重庆两江微链智能科技有限公司 | A kind of intelligent robot beverage preparation system with cognition machint |
| CN109202802A (en) * | 2018-11-14 | 2019-01-15 | 山东大学 | A kind of vision guide system and method for snap-fit |
| CN109214372A (en) * | 2018-11-01 | 2019-01-15 | 深圳蓝胖子机器人有限公司 | Attitude determination method, device and computer readable storage medium |
| CN109472235A (en) * | 2018-11-01 | 2019-03-15 | 深圳蓝胖子机器人有限公司 | Attitude determination method, device and computer readable storage medium |
| CN109969178A (en) * | 2019-03-26 | 2019-07-05 | 齐鲁工业大学 | Based on the autonomous handling device of the more materials of multielement bar and method |
| CN110428465A (en) * | 2019-07-12 | 2019-11-08 | 中国科学院自动化研究所 | View-based access control model and the mechanical arm grasping means of tactile, system, device |
| CN110807969A (en) * | 2019-11-28 | 2020-02-18 | 深圳市华兴鼎盛科技有限公司 | Machine vision recognition teaching system and teaching method |
| CN110936372A (en) * | 2018-09-21 | 2020-03-31 | 许昌学院 | Control system of cigarette carton stacking robot |
| CN111853557A (en) * | 2020-07-28 | 2020-10-30 | 中国水利水电科学研究院 | Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar |
| CN113359706A (en) * | 2021-05-17 | 2021-09-07 | 中国矿业大学 | Multi-body auxiliary transportation system cooperative turning track self-planning system and method |
| CN113591923A (en) * | 2021-07-01 | 2021-11-02 | 四川大学 | Engine rocker arm part classification method based on image feature extraction and template matching |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567449A (en) * | 2010-11-09 | 2012-07-11 | 哈曼贝克自动***股份有限公司 | Vision system and method of analyzing an image |
| CN202604831U (en) * | 2012-04-26 | 2012-12-19 | 西北大学 | Limb motion parameter collecting and processing device |
| CN104794717A (en) * | 2015-04-27 | 2015-07-22 | 中国科学院光电技术研究所 | Binocular vision system based depth information comparison method |
| CN104966101A (en) * | 2015-06-17 | 2015-10-07 | 镇江苏仪德科技有限公司 | Solar cell classification method based on LabVIEW |
| CN105118032A (en) * | 2015-08-19 | 2015-12-02 | 湖南优象科技有限公司 | Wide dynamic processing method based on visual system |
-
2016
- 2016-04-19 CN CN201610244119.2A patent/CN105930854A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567449A (en) * | 2010-11-09 | 2012-07-11 | 哈曼贝克自动***股份有限公司 | Vision system and method of analyzing an image |
| CN202604831U (en) * | 2012-04-26 | 2012-12-19 | 西北大学 | Limb motion parameter collecting and processing device |
| CN104794717A (en) * | 2015-04-27 | 2015-07-22 | 中国科学院光电技术研究所 | Binocular vision system based depth information comparison method |
| CN104966101A (en) * | 2015-06-17 | 2015-10-07 | 镇江苏仪德科技有限公司 | Solar cell classification method based on LabVIEW |
| CN105118032A (en) * | 2015-08-19 | 2015-12-02 | 湖南优象科技有限公司 | Wide dynamic processing method based on visual system |
Non-Patent Citations (2)
| Title |
|---|
| 武文杰等: ""Tripod机器人的视觉处理应用研究"", 《石油化工自动化》 * |
| 陈希岩: ""基于图像的视觉伺服机器人***研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106636510B (en) * | 2016-10-20 | 2019-07-30 | 三峡大学 | It is a kind of that pricker method is moved based on machine vision certainly |
| CN106636510A (en) * | 2016-10-20 | 2017-05-10 | 三峡大学 | Automatic brazing rod changing method based on machine vision |
| CN106846342A (en) * | 2017-02-23 | 2017-06-13 | 东莞市旭海机械有限公司 | A kind of Full-automatic tobacco bag cutting machine |
| CN107272569A (en) * | 2017-08-11 | 2017-10-20 | 重庆邮电大学 | A kind of long-range motion control experimental facility |
| CN108109174A (en) * | 2017-12-13 | 2018-06-01 | 上海电气集团股份有限公司 | A kind of robot monocular bootstrap technique sorted at random for part at random and system |
| CN108109174B (en) * | 2017-12-13 | 2022-02-18 | 上海电气集团股份有限公司 | Robot monocular guidance method and system for randomly sorting scattered parts |
| CN108405374B (en) * | 2018-02-01 | 2024-04-23 | 上海建桥学院 | Automatic distinguish arm pickup system of different colours |
| CN108405374A (en) * | 2018-02-01 | 2018-08-17 | 上海建桥学院 | A kind of mechanical arm picking up system of automatic discrimination different colours |
| CN108480223A (en) * | 2018-03-19 | 2018-09-04 | 厦门理工学院 | A kind of workpiece sorting system and its control method |
| CN108959998A (en) * | 2018-06-25 | 2018-12-07 | 天津英创汇智汽车技术有限公司 | Two-dimensional code identification method, apparatus and system |
| CN108964361A (en) * | 2018-07-14 | 2018-12-07 | 芜湖益浩昌智能设备有限公司 | A kind of driving control system for servo motor |
| CN109191693A (en) * | 2018-07-23 | 2019-01-11 | 重庆两江微链智能科技有限公司 | A kind of intelligent robot beverage preparation system with cognition machint |
| CN110936372A (en) * | 2018-09-21 | 2020-03-31 | 许昌学院 | Control system of cigarette carton stacking robot |
| CN109214372B (en) * | 2018-11-01 | 2021-04-02 | 深圳蓝胖子机器智能有限公司 | Attitude determination method, attitude determination device and computer-readable storage medium |
| CN109472235A (en) * | 2018-11-01 | 2019-03-15 | 深圳蓝胖子机器人有限公司 | Attitude determination method, device and computer readable storage medium |
| CN109214372A (en) * | 2018-11-01 | 2019-01-15 | 深圳蓝胖子机器人有限公司 | Attitude determination method, device and computer readable storage medium |
| CN109202802A (en) * | 2018-11-14 | 2019-01-15 | 山东大学 | A kind of vision guide system and method for snap-fit |
| CN109969178A (en) * | 2019-03-26 | 2019-07-05 | 齐鲁工业大学 | Based on the autonomous handling device of the more materials of multielement bar and method |
| CN110428465A (en) * | 2019-07-12 | 2019-11-08 | 中国科学院自动化研究所 | View-based access control model and the mechanical arm grasping means of tactile, system, device |
| CN110807969A (en) * | 2019-11-28 | 2020-02-18 | 深圳市华兴鼎盛科技有限公司 | Machine vision recognition teaching system and teaching method |
| CN111853557A (en) * | 2020-07-28 | 2020-10-30 | 中国水利水电科学研究院 | Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar |
| CN111853557B (en) * | 2020-07-28 | 2021-06-08 | 中国水利水电科学研究院 | Automatic identification method and system for detecting pipeline leakage based on ground penetrating radar |
| CN113359706A (en) * | 2021-05-17 | 2021-09-07 | 中国矿业大学 | Multi-body auxiliary transportation system cooperative turning track self-planning system and method |
| CN113591923A (en) * | 2021-07-01 | 2021-11-02 | 四川大学 | Engine rocker arm part classification method based on image feature extraction and template matching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105930854A (en) | Manipulator visual system | |
| CN111062915B (en) | Real-time steel pipe defect detection method based on improved YOLOv3 model | |
| CN110647875B (en) | Method for segmenting and identifying model structure of blood cells and blood cell identification method | |
| CN108717524B (en) | Gesture recognition system based on double-camera mobile phone and artificial intelligence system | |
| CN112347887B (en) | Object detection method, object detection device and electronic equipment | |
| CN108596102B (en) | RGB-D-based indoor scene object segmentation classifier construction method | |
| CN108596880A (en) | Weld defect feature extraction based on image procossing and welding quality analysis method | |
| CN107230203A (en) | Casting defect recognition methods based on human eye vision attention mechanism | |
| CN102509085A (en) | Pig walking posture identification system and method based on outline invariant moment features | |
| CN105389581A (en) | Germinated rice germ integrity intelligent identification system and identification method thereof | |
| CN111553949A (en) | Positioning and grabbing method for irregular workpiece based on single-frame RGB-D image deep learning | |
| CN110334727B (en) | Intelligent matching detection method for tunnel cracks | |
| CN110640741A (en) | Grabbing industrial robot with regular-shaped workpiece matching function | |
| CN109781737A (en) | A kind of detection method and its detection system of hose surface defect | |
| CN111161295A (en) | Background stripping method for dish image | |
| CN114004814A (en) | Coal gangue identification method and system based on deep learning and gray scale third moment analysis | |
| CN210161172U (en) | Bottle and can type garbage identification and classification robot based on deep learning | |
| CN105354547A (en) | Pedestrian detection method in combination of texture and color features | |
| An et al. | Automated detection of tuberculosis bacilli using deep neural networks with sputum smear images | |
| CN109993715A (en) | A kind of robot vision image preprocessing system and image processing method | |
| CN112991327A (en) | Steel grid welding system and method based on machine vision and terminal equipment | |
| CN102968618A (en) | Static hand gesture recognition method fused with BoF model and spectral clustering algorithm | |
| CN117330582A (en) | Polymer PE film surface crystal point detecting system | |
| CN117351371A (en) | Remote sensing image target detection method based on deep learning | |
| CN106033537A (en) | Visual identification device and method for robot positioning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160907 |