CN108161930A - A kind of robot positioning system of view-based access control model and method - Google Patents
A kind of robot positioning system of view-based access control model and method Download PDFInfo
- Publication number
- CN108161930A CN108161930A CN201611112172.3A CN201611112172A CN108161930A CN 108161930 A CN108161930 A CN 108161930A CN 201611112172 A CN201611112172 A CN 201611112172A CN 108161930 A CN108161930 A CN 108161930A
- Authority
- CN
- China
- Prior art keywords
- ball
- industrial robot
- control
- machine
- robot
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
Robot positioning system and method the invention discloses a kind of view-based access control model, wherein, the system comprises:Video camera, PC machine, industrial robot controller, industrial machine human body, metal platform and ball.The localization method includes the following steps:S1, cameras capture simultaneously obtain ball image;S2, designed image Processing Algorithm extraction ball and its central coordinate of circle value;S3, design FUZZY ALGORITHMS FOR CONTROL control industrial robot adjusts platform in real time makes ball move to precalculated position.The present invention designs the movement in each joint of FUZZY ALGORITHMS FOR CONTROL control industrial robot using camera collection image, designed image Processing Algorithm detection target object and location, realizes the accurate control to ball movement position.
Description
Technical field
The present invention relates to industrial robot combination computer vision techniques, and in particular to a kind of robot of view-based access control model determines
Position system and method.
Background technology
Computer vision is one and studies the science for how making machine " seeing ", further, just refers to use video camera
It the machine vision such as is identified, tracks and measures to target, and further do graphics process instead of human eye with computer, make at computer
Reason becomes the image for being more suitable for eye-observation or sending instrument detection to.Mainly it is divided to two classes currently based on the localization method of vision,
Two-dimensional visual is positioned to be positioned with three-dimensional modeling.Two-dimensional visual localization method is that picture and surrounding enviroment are carried out to controlling with monocular
Then vision calibration carries out precise manipulation by the coordinate demarcated.And three-dimensional modeling positioning is mainly using 2 and taking the photograph above
As head shoots target, shot image is merged, so as to establish the three-dimensional coordinate of target, emulates three-dimensional environment, it is real
Now to the accurate operation of target.
At present, industrial robot is widely used in industrial production, under the guide operation of staff, can complete to be permitted
More instructions, but robot does not perceive the ability of extraneous information, it is impossible to the working environment that adjustment has changed leads to industry
Things quality is produced with precision by serious influence.Therefore, the Import computer vision technique in industrial machine production, can be with
It improves the precision of industrial robot operation and realizes the function of real-time tracking correction, can meet in production process to robot
Requirement of real-time, and industrial robot is made preferably to adapt to complicated site environment.Domestic industrial robot knot at present
It closes computer vision and is mainly used in being accurately positioned and processing for mechanical technology, such as welding, grinding, Precision Machining and man-machine
Coordinate.
It is inquired by related patents, discovery has following open source literature:
" a kind of automatic film applicator based on machine vision positioning, application number 201610599533.5 " disclose one kind to patent
Based on the automatic film applicator of machine vision positioning, every diaphragm is positioned using machine vision, is inhaled in pad pasting manipulator from film outlet port
After taking diaphragm, first pass through vision system and quickly handle image, and position data is sent to controlling machine box, it is sharp in controlling machine box
Quick error compensation processing is carried out with C language function module and pad pasting process is completed in motion control.
" the steel ball surface defect intelligence annular based on machine vision follows the New Algorithm of inspection, application number to patent
201610615717.6 " propose that a kind of intelligent annular follows inspection algorithm, centered on the center of circle of steel ball in captured image, 50
It is recycled in millisecond to several pixels of interval and draws loop truss successively, counted and calculate the gray value of each pixel, take gray scale
The difference of the maxima and minima of value is compared with threshold values, so as to judge the quality of steel ball.
Analyzed by above-mentioned patent, find existing scheme positioned, detected using machine vision technique, obtain information this
During a little operations, system lacks more accurate algorithm and control errors.
Invention content
The purpose of the present invention is to overcome the deficiency in the prior art, especially solves industrial machine robot in existing technical solution
All be advance off-line teaching or programming, allowing industrial robot when putting into production, good circuit is run according to plan, so as to because
The problem of actual motion track changes caused by installation error, emergency case.A kind of robot of view-based access control model is provided to determine
Position system and method, the system utilize camera collection image, designed image Processing Algorithm detection target object and residing position
It puts, while designs the movement in each joint of FUZZY ALGORITHMS FOR CONTROL control industrial robot, realize the accurate control to ball movement position
System.
In order to solve the above technical problems, the present invention adopts the following technical scheme that:
A kind of robot positioning system of view-based access control model, which is characterized in that the system comprises video camera, PC machine, industry
Robot controller, industrial robot, metal platform and ball.Wherein:
The video camera is mounted on the ring flange of industrial robot end, and the movement for following industrial robot is real-time
Shoot video;The PC machine is connected with industrial robot controller and video camera, carries out the acquisition, transmission and processing of image;Institute
It states industrial robot controller to connect with industrial robot and PC machine, for receiving feedback and the manipulation industrial machine that PC machine transmits
Device people makes ball reach target location;The industrial robot is connected with industrial robot controller and metal platform, realization pair
The accurate control of ball movement position;The metal platform is fixed on industrial robot front end, for placing ball.
The ball localization method that the robot positioning system of view-based access control model is realized, which is characterized in that the method includes
Following steps:
S1, cameras capture simultaneously obtain ball image;
S2, designed image Processing Algorithm extraction ball and its central coordinate of circle value;
S3, design FUZZY ALGORITHMS FOR CONTROL control industrial robot adjusts platform in real time makes ball move to precalculated position.
Description of the drawings
Fig. 1 is the structure diagram of the specific embodiment of the present invention.
Fig. 2 is ball localization method flow chart in the specific embodiment of the present invention.
Fig. 3 is the flow chart of image processing process in the specific embodiment of the present invention.
Fig. 4 is the coordinate diagram for the duality that point-line is represented in the Hough transform algorithm of the present invention.
Fig. 5 be the present invention FUZZY ALGORITHMS FOR CONTROL in abscissa, ordinate error membership function figure.
Fig. 6 be the present invention FUZZY ALGORITHMS FOR CONTROL in abscissa, ordinate error change curve.
Specific embodiment
Below in conjunction with the accompanying drawings and specific embodiment the present invention is carried out in further detail with complete explanation.It is appreciated that
It is that specific embodiment described herein is only used for explaining the present invention rather than limitation of the invention.
Referring to Fig. 1, a kind of robot positioning system of view-based access control model, which is characterized in that the system comprises video camera 1,
PC machine 3, industrial robot controller 4, industrial robot 2, metal platform 5 and ball 6.Wherein:
The video camera 1 is mounted on the ring flange of 2 end of industrial robot, follows the movement of industrial robot 2
Captured in real-time video;The PC machine 3 is connected with industrial robot controller 4 and video camera 1, carry out image acquisition, transmission and
Processing;The industrial robot controller 4 is connect with industrial robot 2 and PC machine 3, for receive the feedback that PC machine 3 transmits with
And manipulating industrial robot 2 makes ball 6 reach target location;The industrial robot 2 and industrial robot controller 4 and metal
Platform 5 is connected, and realizes the accurate control to 6 movement position of ball;The metal platform 5 is fixed on 2 front end of industrial robot, uses
In placement ball 6.
Referring to Fig. 2, ball localization method that the robot positioning system of view-based access control model is realized, which is characterized in that described
Method includes the following steps:
S1, cameras capture simultaneously obtain ball image.
Cmos camera 1 is fixed on the ring flange of 2 end of industrial robot, the movement for following industrial robot 2 is real
When shoot video, by video image obtain target location information.
S2, designed image Processing Algorithm extraction ball and its central coordinate of circle value.
Since collection in worksite environment can be along with influences such as uneven illumination, background interferences, acquiring picture often can be because of each
Kind factor makes income effect undesirable.The characteristics of for acquired image, carries out image preprocessing, and main purpose is extraction ball area
Domain, reducing influences caused by the interference of various factors, convenient for the feature extraction of later stage ball image.Image procossing detailed process
As shown in Figure 3.
S21, image preprocessing.Image processing section mainly realizes gray processing, denoising, binaryzation and the morphology of image
The functions such as processing.Ball image preprocessing in the process carries out gray proces first, so that the later stage carries out precise positioning to ball.
S22, target's feature-extraction.Feature recognition and extraction is the committed step of ball positioning, and whether the feature of extraction closes
Reason will have a major impact subsequent result.Because target object is black ball, circle need to be only detected.Inspection
It surveys round using Canny operators (J Canny.A Computational Approach to Edge Detection.《IEEE
Transactions on Pattern Analysis&Machine Intelligence》.1986,8(6):Side 679-98)
Method carries out edge extracting.Canny operators are smoothed image with Gaussian function, by the part for searching image gradient
Maximum determines object edge.The strong edge detected and weak edge are differentiated using dual threshold, so as to find power
Edge junction, that is, edge breaks position, and these breaking parts are connected.Therefore, which is not easy to be interfered by noise, energy
Weak edge is enough detected suitable for different occasions and edge continuity is preferable.
S23, calculating ball coordinate using Hough transform algorithm, (Yin Xiangyun, Yin Guofu, Hu Xiaobing wait to be based on supporting to swear
Robotic vision system positioning accuracy [J] mechanical engineering journals that amount machine returns, 2011,47 (1):48-54.).Establish image
Space and the correspondence of parameter space, by carrying out simply adding up to complete statistics target detection in parameter space, simultaneously
Boundary curve discontinuous section is connected, which has the characteristics that noise resisting ability is strong.It is detected and justified with Hough transform
When, it needs to establish a three-dimensional cumulative array Array (a, b, r) in parameter space, such as following formula:
Array (a, b, r)=Array (a, b, r)+1 (1)
Its physical significance corresponds to a point in parameter space coordinate system for the circle in rectangular coordinate system, and right angle is sat
A point corresponds to a three-dimensional right circuit cone in parameter space in mark system, so the circle in rectangular coordinate system is determined, just
The intersection point that each circle intersects can be asked in parameter space, which constrains the parameter (a, b, r) by the circle, such as Fig. 4 institutes
Show.
It can be seen that Generalized Hough Transform is that the borderline point of circle in testing image is mapped to three-dimensional parameter space
The conical surface get on, these last circular cones will intersect at certain point (a on parameter space0,b0,r0), and this point is exactly corresponding circle
Heart coordinate and radius.For many distributed image generations, formula 1 can be write as formula (2):
(x-a)2+(y-b)2-r≤ξ (2)
In formula, r is radius, and ξ is the compensation in view of being carried out to image.When Hough transform detection is round, if right in advance
If radius distance value is known nothing, it is desirable to detect that the circle on image just uses method above.On the plane of delineation a little just
Corresponding to a circle under some radius in parameter space, this is actually a circular cone, eventually becomes and finds in parameter space
Peak point.However, the radius of ball of the present invention is it is known that problem has just been simplified to detect specific half from image
The circle of diameter value.Processing procedure becomes to be more prone to, and can be here the center of circle with each foreground point on image, with known half
Diameter adds up in parameter plane upper drawing circle, and result.The peak point in parameter plane is finally found out to get to the center of circle.Through
After crossing Hough transform detection, it is possible to extract ball and its central coordinate of circle value.
S3, design FUZZY ALGORITHMS FOR CONTROL control industrial robot adjusts platform in real time makes ball move to precalculated position.
Control industrial robot is needed after the position coordinates for being extracted ball, ball is made to reach target location, the present invention adopts
With FUZZY ALGORITHMS FOR CONTROL (Guo Xinnian, white Rayleigh, trick matrix and Light-plane calibration method of the flat of Wang Xiu based on active vision
[J] computer engineering and application, 2015,51 (19):56-60.).There are 2 inputs and 2 outputs in this control system,
In, input control quantity is ball and the error of target location, this error is a two-dimensional parametric, and 2 values are respectively on abscissa
Error and ordinate on error.Output quantity is the control signal of industrial robot, and 2 values are respectively the power in abscissa direction
With the power in ordinate direction, ball can be made to be moved in metal platform 5.The input quantity of Fuzzy control system is sat in real time for ball
The error amount of mark and coordinates of targets, difference of the error for transverse and longitudinal coordinate, membership function NB, NM, NS, Z, PS, PM table
Show.Ranging from [- 10 ,+10] of the error of horizontal seat, quantized field are [- 5 ,+5], then quantization factor is 5/10=0.5, error
Membership function, as shown in Fig. 5 (a).
Simulation result shows that the method is effective, the error output of abscissa, as shown in Fig. 6 (a).
Ordinate expression of error is identical with abscissa, and the error range of ordinate is [- 1 ,+1], quantized field for [- 6,
+ 6], then quantization factor be 6/1=6, error membership function, as shown in Fig. 5 (b)
Simulation result shows that the method is effective, the error output of ordinate, as shown in Fig. 6 (b).
Above-mentioned is the preferable embodiment of the present invention, but embodiments of the present invention are not limited by the above,
He it is any without departing from the present invention Spirit Essence with made under principle change, modification, replacement, combine, simplification, should be
The substitute mode of effect, is included within protection scope of the present invention.
Claims (2)
1. a kind of robot positioning system of view-based access control model, which is characterized in that the system comprises video camera, PC machine, industrial machines
Device people controller, industrial robot, metal platform and ball;Wherein:
The video camera is mounted on the ring flange of industrial robot end, follows the movement captured in real-time of industrial robot
Video;The PC machine is connected with industrial robot controller and video camera, carries out the acquisition, transmission and processing of image;The work
Industry robot controller is connect with industrial robot and PC machine, for receiving feedback and the manipulation industrial robot that PC machine transmits
Ball is made to reach target location;The industrial robot is connected with industrial robot controller and metal platform, realizes to ball
The accurate control of movement position;The metal platform is fixed on industrial robot front end, for placing ball.
2. the ball localization method that a kind of robot positioning system using view-based access control model described in claim 1 is realized,
It is characterized in that, the described method comprises the following steps:
S1, cameras capture simultaneously obtain ball image;
S2, designed image Processing Algorithm extraction ball and its central coordinate of circle value;
S3, design FUZZY ALGORITHMS FOR CONTROL control industrial robot adjusts platform in real time makes ball move to precalculated position.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611112172.3A CN108161930A (en) | 2016-12-07 | 2016-12-07 | A kind of robot positioning system of view-based access control model and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611112172.3A CN108161930A (en) | 2016-12-07 | 2016-12-07 | A kind of robot positioning system of view-based access control model and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108161930A true CN108161930A (en) | 2018-06-15 |
Family
ID=62525969
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611112172.3A Pending CN108161930A (en) | 2016-12-07 | 2016-12-07 | A kind of robot positioning system of view-based access control model and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108161930A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109080144A (en) * | 2018-07-10 | 2018-12-25 | 泉州装备制造研究所 | 3D printing spray head end real-time tracking localization method based on central point judgement |
CN109130167A (en) * | 2018-07-11 | 2019-01-04 | 泉州装备制造研究所 | A kind of 3D printing spray head end tracking based on correlation filtering |
CN109177175A (en) * | 2018-07-10 | 2019-01-11 | 泉州装备制造研究所 | A kind of 3D printing spray head end real-time tracking localization method |
CN109211222A (en) * | 2018-08-22 | 2019-01-15 | 扬州大学 | High-accuracy position system and method based on machine vision |
CN109451283A (en) * | 2018-12-21 | 2019-03-08 | 核动力运行研究所 | A kind of steam generator water chamber ambient image acquisition system |
CN113223082A (en) * | 2021-05-12 | 2021-08-06 | 武汉中仪物联技术股份有限公司 | Pipeline scanning method, scanning device, radar crawler and electronic equipment |
-
2016
- 2016-12-07 CN CN201611112172.3A patent/CN108161930A/en active Pending
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109080144A (en) * | 2018-07-10 | 2018-12-25 | 泉州装备制造研究所 | 3D printing spray head end real-time tracking localization method based on central point judgement |
CN109177175A (en) * | 2018-07-10 | 2019-01-11 | 泉州装备制造研究所 | A kind of 3D printing spray head end real-time tracking localization method |
CN109130167A (en) * | 2018-07-11 | 2019-01-04 | 泉州装备制造研究所 | A kind of 3D printing spray head end tracking based on correlation filtering |
CN109211222A (en) * | 2018-08-22 | 2019-01-15 | 扬州大学 | High-accuracy position system and method based on machine vision |
CN109451283A (en) * | 2018-12-21 | 2019-03-08 | 核动力运行研究所 | A kind of steam generator water chamber ambient image acquisition system |
CN113223082A (en) * | 2021-05-12 | 2021-08-06 | 武汉中仪物联技术股份有限公司 | Pipeline scanning method, scanning device, radar crawler and electronic equipment |
CN113223082B (en) * | 2021-05-12 | 2022-08-02 | 武汉中仪物联技术股份有限公司 | Pipeline scanning method, scanning device, radar crawler and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108161930A (en) | A kind of robot positioning system of view-based access control model and method | |
CN102982557B (en) | Method for processing space hand signal gesture command based on depth camera | |
CN108982546B (en) | Intelligent robot gluing quality detection system and method | |
CN109308693B (en) | Single-binocular vision system for target detection and pose measurement constructed by one PTZ camera | |
US20230042756A1 (en) | Autonomous mobile grabbing method for mechanical arm based on visual-haptic fusion under complex illumination condition | |
CN108109174A (en) | A kind of robot monocular bootstrap technique sorted at random for part at random and system | |
CN107992881A (en) | A kind of Robotic Dynamic grasping means and system | |
CN113427168A (en) | Real-time welding seam tracking device and method for welding robot | |
Zou et al. | An end-to-end calibration method for welding robot laser vision systems with deep reinforcement learning | |
Chen et al. | Acquisition of weld seam dimensional position information for arc welding robot based on vision computing | |
CN104400265B (en) | A kind of extracting method of the welding robot corner connection characteristics of weld seam of laser vision guiding | |
CN108177143A (en) | A kind of robot localization grasping means and system based on laser vision guiding | |
CN103203526A (en) | Laser visual tracking system | |
CN112893007A (en) | Dispensing system based on machine vision and dispensing method thereof | |
CN104325268A (en) | Industrial robot three-dimensional space independent assembly method based on intelligent learning | |
CN109297413A (en) | A kind of large-size cylinder body Structural visual measurement method | |
CN111536872B (en) | Two-dimensional plane distance measuring device and method based on vision and mark point identification device | |
JP2015212629A (en) | Detection device and manipulator operation control including detection device | |
CN111645111A (en) | Intelligent manufacturing system and method based on industrial robot | |
CN108032011A (en) | Initial point guiding device and method are stitched based on laser structure flush weld | |
WO2022036478A1 (en) | Machine vision-based augmented reality blind area assembly guidance method | |
Zhang et al. | Literature review of machine vision in application field | |
CN207752527U (en) | A kind of Robotic Dynamic grasping system | |
TWI274845B (en) | Equipment for detecting the object corner and distance using a sole lens | |
Songhui et al. | Objects detection and location based on mask RCNN and stereo vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180615 |