CN107590837A - A kind of vision positioning intelligent precise puts together machines people and its camera vision scaling method - Google Patents
A kind of vision positioning intelligent precise puts together machines people and its camera vision scaling method Download PDFInfo
- Publication number
- CN107590837A CN107590837A CN201710797405.6A CN201710797405A CN107590837A CN 107590837 A CN107590837 A CN 107590837A CN 201710797405 A CN201710797405 A CN 201710797405A CN 107590837 A CN107590837 A CN 107590837A
- Authority
- CN
- China
- Prior art keywords
- camera
- vision
- image
- vision positioning
- coordinate system
- 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
Landscapes
- Image Analysis (AREA)
Abstract
Put together machines people the invention discloses a kind of vision positioning intelligent precise, including at least vision positioning system, the vision positioning system includes treating Assembly part and assembles the servo-actuated camera that position carries out vision positioning, and the fixed camera that the Assembly part to having accommodated on chuck is positioned, each video camera are made up of CCD high definitions industrial camera, high definition industrial lens and LED light source.Camera vision scaling method includes IMAQ, image segmentation, contours extract, object object defects detection, the calculating of object pose parameter：Robot of the present invention uses vision positioning technology, and object is identified, obtains its Position and orientation parameters, realizes that carrying out scene to target object is accurately positioned, live real time kinematics parametric programming.
Description
Technical field
The invention belongs to Industrial Robot Technology field, specifically a kind of vision positioning intelligent precise put together machines people and its
Camera vision scaling method.
Background technology
High-end manufacture needs industrial robot, and industrial transformation upgrading also be unable to do without industrial robot.Industrial robot is real
Apply one of automatic production line, industry 4.0, intelligence manufacture workshop, digital factory, the important foundation of intelligent plant equipment.When
Before, manufacturing industry is being undergone to automate, digitize, the industrial upgrading of the intelligent new round for turning to core, industrial robot skill
The art automated arm important as modern manufacturing industry.Robot technology lifting can directly drive intelligent Manufacturing Technology, material, base
The horizontal lifting of plinth parts, system equipment technology, developing industry robot can directly drive the development of equipment manufacture.
Vision positioning technology is the intelligentized core technology of industrial robot.Vision positioning technology not only overcomes biography
System the shortcomings that method is positioned manually, while the advantages of also played oneself quick and precisely：
(1) position of part can be provided for robot and posture coordinate information, Direct Drive Robot is accurately captured
With precision assembly.
(2) positioning precision is high, and positioning result is reliably, stably；
(3) locating speed is fast, and can work long hours, and can reach 24 hour operation in 24 hours.
In vision positioning detecting system, can accurately identify the direction of product and position be system core.Vision is determined
Position system uses advanced image vision detection technique, realizes that the industrial products of high-speed motion are carried out with comprehensive vision in real time determines
Position analysis.When system one high-performance color digital camera of outfit, camera acquisition industrial goods image, and view data is passed
When being sent to image processing system, image processing system carries out matching search to each image, be accurately positioned out product position and
The automated arm such as direction, control machinery arm.
The content of the invention
It is an object of the invention to provide a kind of vision positioning intelligent precise put together machines people and its camera vision demarcation
Method, realize that carrying out scene to target object is accurately positioned, live real time kinematics parametric programming.
The present invention uses following technical scheme to achieve the above object：
A kind of vision positioning intelligent precise puts together machines people, including at least vision positioning system, the vision positioning system
Including treating Assembly part and assembling the servo-actuated camera of position progress vision positioning, and to having accommodated the Assembly part on chuck
The fixed camera positioned, each video camera are made up of CCD high definitions industrial camera, high definition industrial lens and LED light source.
A kind of vision positioning intelligent precise puts together machines the camera vision scaling method of people, comprises the following steps:
1), IMAQ
The image for including part is obtained by capture card, distortion correction is carried out to image；
2), image is split
LPF in being carried out to original image, the point that enhancing algorithm has significant change gray scale in neighborhood highlight,
Completed by calculating gradient magnitude；Coloured image is converted into gray level image, establishes histogram, is further carried out as needed
Image stretch；
Binary conversion treatment：A certain threshold values is set, everything pixel value is more than the point of the threshold values, makes its value be equal to 255, conversely,
Every pixel value is less than the point of the threshold values, makes its value be equal to 0；Verify " Two-peak method ", " P parametric methods ", " Otsu methods " " maximum entropy valve
The using effect in environment, therefrom selection determine the method for being adapted to robot at the scene for value method " and " iterative method "；
3), contours extract
Carry out just positioning first, using binary image, carry out contour detecting and extraction, to reduce sub-pixel edge detection
The region calculated, then extract profile edge using sub-pixel edge detection method；
4), object object defects detection：
Object characteristics of objects storehouse is established, a contour feature obtained is compared with object characteristics of objects storehouse, it is right
Object carries out profile defect detection, overall size accuracy detection, more profile relative positional accuracy detections；
5), object pose parameter calculates：
For the qualified object object of defects detection, its object own coordinate is calculated first and is tied up in image coordinate system
Coordinate position and angle parameter, then carry out coordinate transform object local Coordinate System is transformed into world coordinate system, from
And pose parameter of the object local Coordinate System in world coordinate system is obtained, and object itself pose parameter is sent to machine
Device people, guided robot carry out trajectory calculation.
The beneficial effects of the invention are as follows：Robot of the present invention uses vision positioning technology, and object is identified, and obtains
Its Position and orientation parameters, realize that carrying out scene to target object is accurately positioned, live real time kinematics parametric programming.
Brief description of the drawings
Fig. 1 is vision positioning schematic diagram of the present invention；
Fig. 2 is camera vision demarcation schematic diagram of the present invention；
Fig. 3 is mounting structure schematic diagram of the present invention.
In figure：1st, plane articulation robot, 2, servo-actuated camera, 3, it is to be installed replace the spare parts, 4, Assembly part, 5, assembling position, 6,
Fixed camera.
Embodiment
The present invention is described in detail with reference to the accompanying drawings and detailed description.
As shown in Figure 1,3, a kind of vision positioning intelligent precise puts together machines people, the robot (plane articulation robot 1)
Including at least vision positioning system, the vision positioning system includes treating Assembly part 3 and assembling position 5 carrying out vision positioning
Servo-actuated camera 2, and the fixed camera 6 that the Assembly part 4 to having accommodated on chuck is positioned, each video camera is by CCD
High definition industrial camera, high definition industrial lens and LED light source composition.
The camera vision scaling method of people as shown in Fig. 2 a kind of vision positioning intelligent precise puts together machines, including it is as follows
Step:
1), IMAQ
The image for including part is obtained by capture card, distortion correction is carried out to image；
2), image is split
LPF in being carried out to original image, the point that enhancing algorithm has significant change gray scale in neighborhood highlight,
Completed by calculating gradient magnitude；Coloured image is converted into gray level image, establishes histogram, is further carried out as needed
Image stretch；
Binary conversion treatment：A certain threshold values is set, everything pixel value is more than the point of the threshold values, makes its value be equal to 255, conversely,
Every pixel value is less than the point of the threshold values, makes its value be equal to 0；Verify " Two-peak method ", " P parametric methods ", " Otsu methods " " maximum entropy valve
The using effect in environment, therefrom selection determine the method for being adapted to robot at the scene for value method " and " iterative method "；
3), contours extract
Carry out just positioning first, using binary image, carry out contour detecting and extraction, to reduce sub-pixel edge detection
The region calculated, then extract profile edge using sub-pixel edge detection method；
4), object object defects detection：
Object characteristics of objects storehouse is established, a contour feature obtained is compared with object characteristics of objects storehouse, it is right
Object carries out profile defect detection, overall size accuracy detection, more profile relative positional accuracy detections；
5), object pose parameter calculates：
For the qualified object object of defects detection, its object own coordinate is calculated first and is tied up in image coordinate system
Coordinate position and angle parameter, then carry out coordinate transform object local Coordinate System is transformed into world coordinate system, from
And pose parameter of the object local Coordinate System in world coordinate system is obtained, and object itself pose parameter is sent to machine
Device people, guided robot carry out trajectory calculation.
Described above is present pre-ferred embodiments, for the ordinary skill in the art, according to the present invention's
Teaching, in the case where not departing from the principle of the present invention and spirit, the changes, modifications, replacement and the change that are carried out to embodiment
Type is still fallen within protection scope of the present invention.
Claims (2)
- The people 1. a kind of vision positioning intelligent precise puts together machines, it is characterised in that including at least vision positioning system, the vision Alignment system includes treating Assembly part and assembles the servo-actuated camera that position carries out vision positioning, and to having accommodated on chuck The fixed camera that Assembly part is positioned, each video camera is by CCD high definitions industrial camera, high definition industrial lens and LED light source Composition.
- The camera vision scaling method of people 2. a kind of vision positioning intelligent precise as claimed in claim 1 puts together machines, its It is characterised by, comprises the following steps:1), IMAQThe image for including part is obtained by capture card, distortion correction is carried out to image；2), image is splitLPF in being carried out to original image, the point that enhancing algorithm has significant change gray scale in neighborhood are highlighted, passed through Gradient magnitude is calculated to complete；Coloured image is converted into gray level image, establishes histogram, further carries out image as needed Stretching；Binary conversion treatment：A certain threshold values is set, everything pixel value is more than the point of the threshold values, makes its value be equal to 255, conversely, every Pixel value is less than the point of the threshold values, makes its value be equal to 0；Verify " Two-peak method ", " P parametric methods ", " Otsu methods " " maximum entropy threshold values The using effect in environment, therefrom selection determine the method for being adapted to robot at the scene for method " and " iterative method "；3), contours extractCarry out just positioning first, using binary image, carry out contour detecting and extraction, to reduce in terms of sub-pixel edge detection institute The region of calculation, then extract profile edge using sub-pixel edge detection method；4), object object defects detection：Object characteristics of objects storehouse is established, a contour feature obtained is compared with object characteristics of objects storehouse, to target Thing carries out profile defect detection, overall size accuracy detection, more profile relative positional accuracy detections；5), object pose parameter calculates：For the qualified object object of defects detection, the seat that its object own coordinate is tied up in image coordinate system is calculated first Cursor position and angle parameter, then carry out coordinate transform and object local Coordinate System is transformed into world coordinate system, so as to Machine is sent to pose parameter of the object local Coordinate System in world coordinate system, and by object itself pose parameter People, guided robot carry out trajectory calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710797405.6A CN107590837A (en) | 2017-09-06 | 2017-09-06 | A kind of vision positioning intelligent precise puts together machines people and its camera vision scaling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710797405.6A CN107590837A (en) | 2017-09-06 | 2017-09-06 | A kind of vision positioning intelligent precise puts together machines people and its camera vision scaling method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107590837A true CN107590837A (en) | 2018-01-16 |
Family
ID=61051344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710797405.6A Pending CN107590837A (en) | 2017-09-06 | 2017-09-06 | A kind of vision positioning intelligent precise puts together machines people and its camera vision scaling method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107590837A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108311859A (en) * | 2018-01-22 | 2018-07-24 | 安徽慧视金瞳科技有限公司 | A kind of insulator automatic assembly method of view-based access control model detection technique |
| CN108636830A (en) * | 2018-05-10 | 2018-10-12 | 苏州大学 | The method, apparatus and equipment of defective capsule detection sorting based on machine vision |
| CN108845572A (en) * | 2018-05-29 | 2018-11-20 | 盐城工学院 | A kind of industrial carrying machine people's localization method |
| CN109551195A (en) * | 2018-11-28 | 2019-04-02 | 合肥常青机械股份有限公司 | A kind of auto parts precision assembly vision measurement system and method |
| CN109591013A (en) * | 2018-12-12 | 2019-04-09 | 山东大学 | A kind of flexible assembly analogue system and its implementation |
| CN110480306A (en) * | 2019-07-09 | 2019-11-22 | 金榀精密工业(苏州)有限公司 | Intelligent locating formula intelligent casting component assembly method |
| CN110516618A (en) * | 2019-08-29 | 2019-11-29 | 苏州大学 | Put together machines the assembly method and system of people and view-based access control model and force-location mix control |
| CN111421425A (en) * | 2020-03-11 | 2020-07-17 | 东北大学 | Metal surface grinding system based on industrial vision |
| CN111694423A (en) * | 2019-03-12 | 2020-09-22 | 阿里巴巴集团控股有限公司 | Positioning, capturing, data processing and display method and equipment for augmented reality |
| CN112894815A (en) * | 2021-01-25 | 2021-06-04 | 西安工业大学 | Method for detecting optimal position and posture for article grabbing by visual servo mechanical arm |
| CN113145942A (en) * | 2021-03-12 | 2021-07-23 | 重庆市永川区中川科技发展有限责任公司 | Work control method of gear shaping machine |
| CN113146172A (en) * | 2021-03-08 | 2021-07-23 | 中国科学院宁波材料技术与工程研究所 | Multi-vision-based detection and assembly system and method |
| CN116245877A (en) * | 2023-05-08 | 2023-06-09 | 济南达宝文汽车设备工程有限公司 | Material frame detection method and system based on machine vision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1724999A (en) * | 2004-07-21 | 2006-01-25 | 欧姆龙株式会社 | Methods of and apparatus for inspecting substrate |
| CN106053479A (en) * | 2016-07-21 | 2016-10-26 | 湘潭大学 | System for visually detecting workpiece appearance defects based on image processing |
| CN106272416A (en) * | 2016-08-29 | 2017-01-04 | 上海交通大学 | Feel based on power and the robot slender axles Fine Boring system and method for vision |
| CN106846404A (en) * | 2017-01-16 | 2017-06-13 | 河海大学常州校区 | A kind of quick position and posture detection method based on workpiece inside and outside contour geometric properties |
-
2017
- 2017-09-06 CN CN201710797405.6A patent/CN107590837A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1724999A (en) * | 2004-07-21 | 2006-01-25 | 欧姆龙株式会社 | Methods of and apparatus for inspecting substrate |
| CN106053479A (en) * | 2016-07-21 | 2016-10-26 | 湘潭大学 | System for visually detecting workpiece appearance defects based on image processing |
| CN106272416A (en) * | 2016-08-29 | 2017-01-04 | 上海交通大学 | Feel based on power and the robot slender axles Fine Boring system and method for vision |
| CN106846404A (en) * | 2017-01-16 | 2017-06-13 | 河海大学常州校区 | A kind of quick position and posture detection method based on workpiece inside and outside contour geometric properties |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108311859A (en) * | 2018-01-22 | 2018-07-24 | 安徽慧视金瞳科技有限公司 | A kind of insulator automatic assembly method of view-based access control model detection technique |
| CN108636830A (en) * | 2018-05-10 | 2018-10-12 | 苏州大学 | The method, apparatus and equipment of defective capsule detection sorting based on machine vision |
| CN108845572A (en) * | 2018-05-29 | 2018-11-20 | 盐城工学院 | A kind of industrial carrying machine people's localization method |
| CN109551195A (en) * | 2018-11-28 | 2019-04-02 | 合肥常青机械股份有限公司 | A kind of auto parts precision assembly vision measurement system and method |
| CN109591013A (en) * | 2018-12-12 | 2019-04-09 | 山东大学 | A kind of flexible assembly analogue system and its implementation |
| CN111694423A (en) * | 2019-03-12 | 2020-09-22 | 阿里巴巴集团控股有限公司 | Positioning, capturing, data processing and display method and equipment for augmented reality |
| CN111694423B (en) * | 2019-03-12 | 2023-05-26 | 阿里巴巴集团控股有限公司 | Positioning, grabbing, data processing and display method and device for augmented reality |
| CN110480306A (en) * | 2019-07-09 | 2019-11-22 | 金榀精密工业(苏州)有限公司 | Intelligent locating formula intelligent casting component assembly method |
| CN110516618A (en) * | 2019-08-29 | 2019-11-29 | 苏州大学 | Put together machines the assembly method and system of people and view-based access control model and force-location mix control |
| CN110516618B (en) * | 2019-08-29 | 2022-04-12 | 苏州大学 | Assembly robot and assembly method and system based on vision and force position hybrid control |
| CN111421425A (en) * | 2020-03-11 | 2020-07-17 | 东北大学 | Metal surface grinding system based on industrial vision |
| CN112894815A (en) * | 2021-01-25 | 2021-06-04 | 西安工业大学 | Method for detecting optimal position and posture for article grabbing by visual servo mechanical arm |
| CN112894815B (en) * | 2021-01-25 | 2022-09-27 | 西安工业大学 | Method for detecting optimal position and posture for article grabbing by visual servo mechanical arm |
| CN113146172A (en) * | 2021-03-08 | 2021-07-23 | 中国科学院宁波材料技术与工程研究所 | Multi-vision-based detection and assembly system and method |
| CN113145942A (en) * | 2021-03-12 | 2021-07-23 | 重庆市永川区中川科技发展有限责任公司 | Work control method of gear shaping machine |
| CN116245877A (en) * | 2023-05-08 | 2023-06-09 | 济南达宝文汽车设备工程有限公司 | Material frame detection method and system based on machine vision |
| CN116245877B (en) * | 2023-05-08 | 2023-11-03 | 济南达宝文汽车设备工程有限公司 | Material frame detection method and system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107590837A (en) | A kind of vision positioning intelligent precise puts together machines people and its camera vision scaling method | |
| CN107767423B (en) | mechanical arm target positioning and grabbing method based on binocular vision | |
| CN109785317B (en) | Automatic pile up neatly truss robot's vision system | |
| CN107804514B (en) | Toothbrush sorting method based on image recognition | |
| CN107263468B (en) | SCARA robot assembly method using digital image processing technology | |
| CN106935683B (en) | A kind of positioning of solar battery sheet SPEED VISION and correction system and its method | |
| CN110293559B (en) | Installation method for automatically identifying, positioning and aligning | |
| CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
| CN105690393A (en) | Four-axle parallel robot sorting system based on machine vision and sorting method thereof | |
| CN112893007A (en) | Dispensing system based on machine vision and dispensing method thereof | |
| CN110108712A (en) | Multifunctional visual sense defect detecting system | |
| CN104299246A (en) | Production line object part motion detection and tracking method based on videos | |
| CN114425776A (en) | Automatic labeling positioning and deviation rectifying method based on computer vision | |
| CN115830018B (en) | Carbon block detection method and system based on deep learning and binocular vision | |
| CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
| CN115760782B (en) | Machine vision-based in-mold labeling offset defect identification method | |
| CN115456999B (en) | Saw chain surface defect automatic detection system and defect detection method based on machine vision | |
| CN113744247A (en) | PCB welding spot defect identification method and system | |
| Jia et al. | Real-time color-based sorting robotic arm system | |
| CN207752527U (en) | A kind of Robotic Dynamic grasping system | |
| CN205552536U (en) | Four -axis parallel robot letter sorting system based on machine vision | |
| Xiao-Lian et al. | Identification and location of picking tomatoes based on machine vision | |
| CN111062387B (en) | Identification method, grabbing method and related equipment for articles on conveyor belt | |
| Qian et al. | The autonomous detection of sheet metal parts using imageprocessing | |
| CN107177912A (en) | A kind of automatic doffer control system with vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180116 |