CN108921891A - A kind of machine vision method for rapidly positioning that can arbitrarily rotate - Google Patents
A kind of machine vision method for rapidly positioning that can arbitrarily rotate Download PDFInfo
- Publication number
- CN108921891A CN108921891A CN201810642725.9A CN201810642725A CN108921891A CN 108921891 A CN108921891 A CN 108921891A CN 201810642725 A CN201810642725 A CN 201810642725A CN 108921891 A CN108921891 A CN 108921891A
- Authority
- CN
- China
- Prior art keywords
- square deviation
- mean square
- image
- mean value
- value
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Abstract
The present invention is a kind of machine vision method for rapidly positioning that can arbitrarily rotate, pass through the target and label positioned needed for choosing, it can be achieved not influenced that the effect quickly accurately positioned can be carried out to the target of any direction by made thing body direction with the selected target that navigates to of fast accurate, the present invention in the picture constantly refreshed later.
Description
Technical field
The present invention relates to the machine vision method for rapidly positioning that one kind can arbitrarily rotate.
Background technique
During industrial production, need to carry out article produced the detection or knowledge of quality in many cases
Not specific target.Have under traditional mode through human eye and carry out detection identification, but detection time is long, precision is low, stablizes
Property difference and also there is certain risk under certain special occasions, so machine vision is begun to instead of artificial view
Feel, especially in the case where the higher production of high-speed production detection the degree of automation detects, the benefit of machine vision is just especially
Obviously.For human vision, machine vision have high speed, high-precision, ultraphotic, microspur, it is objective, without fatigue, environmental restrictions
The advantages that.
Summary of the invention
It is an object of the invention to overcome existing defect, provide that a kind of do not influenced by made thing body direction can be to appointing
The target in meaning direction carries out the method quickly accurately positioned.
The purpose of the present invention is achieved through the following technical solutions：A kind of quick side of positioning of the machine vision that can arbitrarily rotate
Method, steps are as follows：
（One）, reduce picture and carry out Primary Location；
Firstly, obtaining the size and histogram of selected areas, calculating mean value and mean square deviation and recording numerical value is A, then with identical
Size shape is as standard, based on the standard, constantly to obtain histogram by pixel translation and calculate equal in picture
Value B and mean square deviation C, finally, when from the comparison domain obtained in picture mean value, mean square deviation and the mean value of target area,
When variance is similar, obtains the area coordinate and complete Primary Location；
（Two）, be accurately positioned；
Accurate positioning is that selected areas carries out in Primary Location, comparison domain is zoomed to the script size of image, slightly
On the basis of expanding comparison domain, mean value and mean square deviation are compared by detection to determine accurate position of the target area in original image
It sets, to complete to be accurately positioned；
（Three）, rotation estimation；
By the rectangular coordinates transformation of image in selected areas to polar coordinates, by judging polar translational movement come the rotation to image
Gyration carries out estimation operation, so that posting can accurately be marked in target area.
In conclusion the present invention has the following advantages that：More traditional positioning has more quick treatment effeciency, Neng Goushi
High speed detection is answered, the efficiency of automation industry detection can be improved, accelerates the production detection of product, while the localization method can be with
It is not influenced by this detection image display orientation, can detecte the picture for identifying each rotation angle, suitable application area is more, flexibility
By force.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Specific embodiment
In order to deepen the understanding of the present invention, below in conjunction with embodiment and attached drawing, the invention will be further described, should
The examples are only for explaining the invention, is not intended to limit the scope of the present invention..
According to Fig. 1, the present invention provides the machine vision method for rapidly positioning that one kind can arbitrarily rotate, specific steps
To reduce picture and carrying out Primary Location；
Firstly, obtaining the size and histogram of selected areas, calculating mean value and mean square deviation and recording numerical value is A, and A is the equal of template
Value and mean square deviation, change according to comparison other, then using same size shape as standard, using the standard as base in picture
Plinth constantly obtains histogram by pixel translation and calculates mean value B and mean square deviation C, compares histogram, finally, working as from picture
When mean value, mean square deviation in the comparison domain of middle acquisition are similar to the mean value of target area, mean square deviation, maximum is taken, obtains the area
Domain coordinate completes Primary Location, and δ is the certain ratio value subtracted when calculating minimum mean and mean square deviation, can be changed.Here
Method only schematically illustrates more the smallest mean value and mean square deviation, and symbol when more maximum mean value or mean square deviation in flow chart negates
?；
It is accurately positioned；
Accurate positioning is that selected areas carries out in Primary Location, comparison domain is zoomed to the script size of image, slightly
On the basis of expanding comparison domain, compare histogram and take maximum, mean value and mean square deviation are compared by detection to determine target area
Accurate location in original image, to complete to be accurately positioned；δ is the certain ratio subtracted when calculating minimum mean and mean square deviation
Example value, can be changed.Here method only schematically illustrates more the smallest mean value and mean square deviation, and when more maximum mean value or mean square deviation flows
Symbol in journey figure negates；
Rotation estimation；
By the rectangular coordinates transformation of image in selected areas to polar coordinates, by judging polar translational movement come the rotation to image
Gyration carries out estimation operation, so that posting can accurately be marked in target area.
The more traditional positioning of this method, has more quick processing, can adapt to high speed detection, automatic production can be improved
The efficiency of industry detection accelerates the production detection of product.The localization method can not be by the shadow of this detection image display orientation simultaneously
It rings, can detecte the picture for identifying each rotation angle, suitable application area is more, strong flexibility.
Claims (1)
1. the machine vision method for rapidly positioning that one kind can arbitrarily rotate, it is characterised in that：Steps are as follows：
（One）, reduce picture and carry out Primary Location；
Firstly, obtaining the size and histogram of selected areas, calculating mean value and mean square deviation and recording numerical value is A, then with identical
Size shape is as standard, based on the standard, constantly to obtain histogram by pixel translation and calculate equal in picture
Value B and mean square deviation C, finally, when from the comparison domain obtained in picture mean value, mean square deviation and the mean value of target area,
When variance is similar, obtains the area coordinate and complete Primary Location；
（Two）, be accurately positioned；
Accurate positioning is that selected areas carries out in Primary Location, comparison domain is zoomed to the script size of image, slightly
On the basis of expanding comparison domain, mean value and mean square deviation are compared by detection to determine accurate position of the target area in original image
It sets, to complete to be accurately positioned；
（Three）, rotation estimation；
By the rectangular coordinates transformation of image in selected areas to polar coordinates, by judging polar translational movement come the rotation to image
Gyration carries out estimation operation, so that posting can accurately be marked in target area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810642725.9A CN108921891A (en) | 2018-06-21 | 2018-06-21 | A kind of machine vision method for rapidly positioning that can arbitrarily rotate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810642725.9A CN108921891A (en) | 2018-06-21 | 2018-06-21 | A kind of machine vision method for rapidly positioning that can arbitrarily rotate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108921891A true CN108921891A (en) | 2018-11-30 |
Family
ID=64419796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810642725.9A Pending CN108921891A (en) | 2018-06-21 | 2018-06-21 | A kind of machine vision method for rapidly positioning that can arbitrarily rotate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108921891A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117487A (en) * | 2011-02-25 | 2011-07-06 | 南京大学 | Scale-direction self-adaptive Mean-shift tracking method aiming at video moving object |
| CN103810478A (en) * | 2014-02-21 | 2014-05-21 | 广东小天才科技有限公司 | Sitting posture detection method and device |
| CN105335985A (en) * | 2014-08-01 | 2016-02-17 | 深圳中集天达空港设备有限公司 | Real-time capture method and system of docking airplane on the basis of machine vision |
| WO2016142546A1 (en) * | 2015-03-11 | 2016-09-15 | Technische Universität München | Ranging method and apparatus |
| CN106067172A (en) * | 2016-05-27 | 2016-11-02 | 哈尔滨工程大学 | A kind of underwater topography image based on suitability analysis slightly mates and mates, with essence, the method combined |
| CN106485749A (en) * | 2016-10-19 | 2017-03-08 | 哈尔滨工业大学 | A kind of rectangular pins element rough localization method based on angle point |
-
2018
- 2018-06-21 CN CN201810642725.9A patent/CN108921891A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117487A (en) * | 2011-02-25 | 2011-07-06 | 南京大学 | Scale-direction self-adaptive Mean-shift tracking method aiming at video moving object |
| CN103810478A (en) * | 2014-02-21 | 2014-05-21 | 广东小天才科技有限公司 | Sitting posture detection method and device |
| CN105335985A (en) * | 2014-08-01 | 2016-02-17 | 深圳中集天达空港设备有限公司 | Real-time capture method and system of docking airplane on the basis of machine vision |
| WO2016142546A1 (en) * | 2015-03-11 | 2016-09-15 | Technische Universität München | Ranging method and apparatus |
| CN106067172A (en) * | 2016-05-27 | 2016-11-02 | 哈尔滨工程大学 | A kind of underwater topography image based on suitability analysis slightly mates and mates, with essence, the method combined |
| CN106485749A (en) * | 2016-10-19 | 2017-03-08 | 哈尔滨工业大学 | A kind of rectangular pins element rough localization method based on angle point |
Non-Patent Citations (2)
| Title |
|---|
| DU-MING TSAI ET AL: ""Machine Vision-Based Positioning and Inspection Using Expectation–Maximization Technique"", 《IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT》 * |
| 潘鹏举: ""基于图像匹配的大视角目标快速精确定位关键技术研究"", 《中国优秀硕士学位论文全文数据库》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103499297B (en) | A kind of high-precision measuring method based on CCD | |
| CN107341802B (en) | Corner sub-pixel positioning method based on curvature and gray scale compounding | |
| CN106251353A (en) | Weak texture workpiece and the recognition detection method and system of three-dimensional pose thereof | |
| JP6899189B2 (en) | Systems and methods for efficiently scoring probes in images with a vision system | |
| CN111531407B (en) | Workpiece attitude rapid measurement method based on image processing | |
| CN104732536A (en) | Sub-pixel edge detection method based on improved morphology | |
| CN107292869B (en) | Image speckle detection method based on anisotropic Gaussian kernel and gradient search | |
| CN107957246B (en) | binocular vision-based method for measuring geometric dimension of object on conveyor belt | |
| CN109035214A (en) | A kind of industrial robot material shapes recognition methods | |
| CN108182704A (en) | Localization method based on Shape context feature | |
| CN104515502A (en) | Robot hand-eye stereo vision measurement method | |
| CN105991913A (en) | Method for location of feature object based on machine vision | |
| CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
| CN115752295A (en) | Automatic hand-eye calibration method for line laser profilometer | |
| CN108399630B (en) | Method for quickly measuring distance of target in region of interest in complex scene | |
| CN108921891A (en) | A kind of machine vision method for rapidly positioning that can arbitrarily rotate | |
| CN110969357A (en) | Visual detection method for holes of aluminum alloy machined part | |
| Wolnitza et al. | 3D object reconstruction and 6D-pose estimation from 2D shape for robotic grasping of objects | |
| CN206912816U (en) | Identify the device of mechanical workpieces pose | |
| CN107020545A (en) | The apparatus and method for recognizing mechanical workpieces pose | |
| Yan et al. | Research of Sub-pixel Inner Diameter Measurement of Workpiece Based on OpenCV | |
| CN112529869A (en) | Valve sleeve throttling square hole detection method | |
| Ulrich et al. | High-accuracy 3D image stitching for robot-based inspection systems | |
| CN107545587B (en) | Round steel end face binocular vision positioning method based on main and auxiliary eyes | |
| CN106845033B (en) | A kind of spray painting spray gun covering of the fan angle of view-based access control model and uniformity modeling method |
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 |
Application publication date: 20181130 |
|
| RJ01 | Rejection of invention patent application after publication |