CN107436124A - A kind of more stitch components positioning of view-based access control model and stitch error detection method - Google Patents
A kind of more stitch components positioning of view-based access control model and stitch error detection method Download PDFInfo
- Publication number
- CN107436124A CN107436124A CN201610353616.6A CN201610353616A CN107436124A CN 107436124 A CN107436124 A CN 107436124A CN 201610353616 A CN201610353616 A CN 201610353616A CN 107436124 A CN107436124 A CN 107436124A
- Authority
- CN
- China
- Prior art keywords
- stitch
- component
- error
- theoretical
- coordinate
- 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
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
Abstract
The invention discloses a kind of positioning of more stitch components of view-based access control model and stitch error detection method, belong to computer vision field.Known to each stitch theoretical coordinate of component, target image is gathered using a ccd video camera demarcated, the error function of each stitch is established according to each stitch theoretical coordinate of component and the Measured Coordinates under CCD camera first, then the gradient matrix and least square solution for rotating against translation relation between the two are calculated, finally give theoretical initial value successive ignition and obtain rotation translation relation of each stitch Measured Coordinates of component relative to theoretical coordinate, and the relative error of each stitch is obtained according to error function.
Description
Technical field
The present invention relates to computer vision field, more particularly to more stitch component positioning and each stitch error detection side
Method.
Background technology
With the development of sensor technology, network technology image technique, the location technology of view-based access control model turns into one
Door fast-developing new discipline, it is positioned in robot navigation, aerospace flight vehicle in the technologies such as crawl, virtual reality
More and more extensive application is obtained.
During the processing and manufacturing of electric equipment products, substantial amounts of more stitch component inserting operations be present.Automatic
Insert in equipment, the detection of component stitch error and the basis that positioning is that this kind of component inserts automatically.Inventor is in the present invention
During, the problem is abstracted as to the rotation translation relation solved between two groups of two-dimemsional number strong points, so as to pass through Gauss-Newton
Method iterates to calculate the rotation translation relation between component stitch Measured Coordinates and theoretical coordinate and obtains each stitch relative to reason
It is good by the error of position, this method strong robustness, fault tolerance, there is very high engineering application value.
The content of the invention
A kind of more stitch components positioning of view-based access control model and stitch error detection method, it is characterised in that pass through Gauss ox
The method of pausing calculates the space that each stitch vision Measured Coordinates of component translate relational implementation component relative to the rotation of theoretical coordinate
Positioning and the error-detecting of each stitch, the described method comprises the following steps:
(1) vision sensor adopts component image, calculates coordinate of each stitch of component under camera coordinate system
(2) error function of each stitch vision Measured Coordinates of component relative to theoretical coordinate is established
(3) gradient matrix and most that translation relation is rotated between each stitch Measured Coordinates relative theory coordinate of component is calculated
A young waiter in a wineshop or an inn multiplies solution
(4) give theoretical initial value successive ignition and obtain rotary flat of each stitch Measured Coordinates of component relative to theoretical coordinate
The error of shifting relation and each stitch
Step (1) is specially:CCD camera gathers component photo, and obtains n stitch components by image processing algorithm
The Measured Coordinates Q of each stitchi=(xi, yi)T(1≤i≤n)
Step (3) is specially:, Pi=(Xi, Yi)TFor each stitch theoretical coordinate of component, Qi=(xi, yi)TIt is each for component
Measured Coordinates of the stitch under CCD camera, θ are rotation relationship between the two, (Tx, Ty)TFor translation relation between the two,
Establish error function
It is specially in step (3):By error write as gradient matrix be multiplied by rotation translation relation form:
Wherein,Δ P=[Δ θ Δs Tx ΔTy]T
Δ P least square solution is:
Δ P=(ATA)-1ATε
Step (4) is specially:Give theoretical initial value P0=[θ0 Tx0 Ty0]T, through multiple least-squares iteration, you can
To each stitch of component relationship delta P and each stitch error are translated relative to the rotation of theoretical coordinate
Brief description of the drawings
Fig. 1 is component detects schematic diagram provided by the invention;
Fig. 2 is each stitch Parameter Map of 10A relays in example provided by the invention
Fig. 3 is the flow chart of more stitch component error-detectings provided by the invention and localization method;
Fig. 4 is detection figure in testing ground provided by the invention
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to embodiment party of the present invention
Formula is described in further detail.
The space orientation of object is quickly and accurately realized for convenience, and the embodiment of the present invention provides more stitch component pins
Pin error-detecting and localization method, referring to Fig. 1-3, this method content is as follows:
Fig. 1 includes:Component 1, light source 2 and CCD camera 3 to be measured.Component to be measured is as above light source during IMAQ.
CCD camera 3 is demarcated in advance, component stitch Measured Coordinates Qi=(xi, yi)T(1≤i≤n) is carried out under camera coordinates system
Measurement.Component establishment of coordinate system is as shown in the figure on component, the theoretical coordinate P of each stitchi=(Xi, Yi)T(1≤i≤n)
Measured under component coordinate system.The rotation relationship of θ expressions between the two is defined, defines (Tx, Ty)TFor between the two
Translation relation.
101:Vision sensor gathers piece image, and obtains the Measured Coordinates Q of each stitch by image processing algorithmi=
(xi, yi)T;
102:Establish error function
103:By error write as gradient matrix be multiplied by rotation translation relation form:
Wherein,Δ P=[Δ θ Δs Tx ΔTy]T
The least square solution that Δ P can be obtained is:
Δ P=(ATA)-1ATε
104:By theoretical initial value P0=[θ0 Tx0 Ty0]TΔ P least square solution is substituted into, successive ignition both obtains the component
Rotation translation relation θ, T between stitch Measured Coordinates and theoretical coordinatexAnd Ty, being substituted into error function can each stitch
Error
The embodiment of the present invention detects experiment to verify the validity of method provided by the invention with 20A relays stitch.Respectively
Stitch theoretical coordinate is
Parameter | X | Y |
No. 1 | 0 | 0 |
No. 2 | 15.06 | 0 |
No. 3 | 15.06 | 7.62 |
No. 4 | 2.46 | 7.62 |
Robot crawl 20A relays are run to above camera, it are detected according to the method for the invention, each pin
Pin measured value is as shown in the table
By theoretical initial value P0=[1.57 176-548]TLeast square solution is substituted into, is selected between the two after 5 iteration
Select translation relation, P5=[1.561 176.32-548.04]T, each stitch error is
Parameter | εx | εy |
No. 1 | 0.133 | 0.111 |
No. 2 | -0.156 | 0.170 |
No. 3 | 0.121 | -0.143 |
No. 4 | -0.147 | -0.139 |
By taking material object as an example, control industrial robot completes the automatic instrumentation operations of the component, and False Rate is less than 0.5%,
Insert fraction defective and be less than 0.5%, the validity of this method has obtained good checking.
Pass through above-mentioned experimental verification, it can be seen that the feasibility of method provided in an embodiment of the present invention, can be with practical application
In to object positioning needs.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the embodiments of the present invention
Sequence number is for illustration only, does not represent the quality of embodiment.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.
Claims (4)
1. a kind of more stitch components positioning of view-based access control model and stitch error detection method, it is characterised in that pass through Gauss-Newton
Method calculates each stitch vision Measured Coordinates of component and determined relative to the space of the rotation translation relational implementation component of theoretical coordinate
Position and the error-detecting of each stitch, the described method comprises the following steps:
(1) vision sensor adopts component image, calculates coordinate of each stitch of component under camera coordinate system
(2) error function of each stitch vision Measured Coordinates of component relative to theoretical coordinate is established
(3) gradient matrix of translation relation and a most young waiter in a wineshop or an inn are rotated between calculating each stitch Measured Coordinates relative theory coordinate of component
Multiply solution
(4) give theoretical initial value successive ignition and obtain rotation translation pass of each stitch Measured Coordinates of component relative to theoretical coordinate
System and the error of each stitch.
2. according to the method for claim 1, it is characterised in that step (2) is specially:
For the component of n stitch, Pi=(Xi, Yi)T(1≤i≤n) is each stitch theoretical coordinate of component, Qi=(xi, yi)T
For Measured Coordinates of each stitch of component under CCD camera, θ is rotation relationship between the two, (Tx, Ty)TFor between the two
Translation relation, establish error function
。
3. according to the method for claim 1, it is characterised in that be specially in step (3):
By error write as gradient matrix be multiplied by rotation translation relation form:
ε≈A·ΔP
Wherein, Δ P=[Δ θ Δs Tx ΔTy]T
Δ P least square solution is:
Δ P=(ATA)-1ATε 。
4. according to the method for claim 1, it is characterised in that step (4) is specially:
Give theoretical initial value P0=[θ0 Tx0 Ty0]T, through multiple least-squares iteration, you can it is relative to obtain each stitch of component
Relationship delta P and each stitch error are translated in the rotation of theoretical coordinate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610353616.6A CN107436124A (en) | 2016-05-26 | 2016-05-26 | A kind of more stitch components positioning of view-based access control model and stitch error detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610353616.6A CN107436124A (en) | 2016-05-26 | 2016-05-26 | A kind of more stitch components positioning of view-based access control model and stitch error detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107436124A true CN107436124A (en) | 2017-12-05 |
Family
ID=60453240
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610353616.6A Pending CN107436124A (en) | 2016-05-26 | 2016-05-26 | A kind of more stitch components positioning of view-based access control model and stitch error detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107436124A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008232950A (en) * | 2007-03-22 | 2008-10-02 | Honda Motor Co Ltd | Position detection method and position detector |
CN102519441A (en) * | 2011-12-06 | 2012-06-27 | 南京航空航天大学 | Method for measuring positioning points based on laser tracker in docking process of airplane parts |
CN102589437A (en) * | 2012-03-09 | 2012-07-18 | 天津大学 | Calibration method for measuring head center position in light pen-type portable three-coordinate measuring system |
CN104215185A (en) * | 2014-09-12 | 2014-12-17 | 国家电网公司 | Method for calibrating central position of transformer by virtue of light-pen type portable three-coordinate measurement system |
CN104359402A (en) * | 2014-11-17 | 2015-02-18 | 南京工业大学 | Detection method for rectangular pin component visual positioning |
-
2016
- 2016-05-26 CN CN201610353616.6A patent/CN107436124A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008232950A (en) * | 2007-03-22 | 2008-10-02 | Honda Motor Co Ltd | Position detection method and position detector |
CN102519441A (en) * | 2011-12-06 | 2012-06-27 | 南京航空航天大学 | Method for measuring positioning points based on laser tracker in docking process of airplane parts |
CN102589437A (en) * | 2012-03-09 | 2012-07-18 | 天津大学 | Calibration method for measuring head center position in light pen-type portable three-coordinate measuring system |
CN104215185A (en) * | 2014-09-12 | 2014-12-17 | 国家电网公司 | Method for calibrating central position of transformer by virtue of light-pen type portable three-coordinate measurement system |
CN104359402A (en) * | 2014-11-17 | 2015-02-18 | 南京工业大学 | Detection method for rectangular pin component visual positioning |
Non-Patent Citations (5)
Title |
---|
方兴 等: "三维坐标转换的通用整体最小二乘算法", 《测绘学报》 * |
李秦川 等: "SO型元件贴装过程中的视觉形位检测", 《计算机测量与控制》 * |
罗长林 等: "基于改进的高斯_牛顿法的非线性三维直角坐标转换方法研究", 《大地测量与地球动力学》 * |
陈宇 等: "基于非线性最小二乘算法的空间坐标转换", 《大地测量与地球动力学》 * |
麦倩: "基于配准的新型表面贴装元器件的定位算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ricolfe-Viala et al. | Using the camera pin-hole model restrictions to calibrate the lens distortion model | |
Bentolila et al. | Conic epipolar constraints from affine correspondences | |
CN104392476A (en) | Method of extracting three-dimensional axis of tunnel based on minimum bounding box algorithm | |
CN104374338A (en) | Single-axis rotation angle vision measurement method based on fixed camera and single target | |
CN109978991B (en) | Method for rapidly realizing online measurement of complex component clamping pose error based on vision | |
CN103234496B (en) | A kind of High-precision correction method of three coordinate measuring machine two-dimensional stage error | |
CN106127758A (en) | A kind of visible detection method based on virtual reality technology and device | |
CN109798921A (en) | Calibration method in a kind of star sensor elements of interior orientation room | |
CN104268837B (en) | Electronic speckle interference fringe pattern phase information extracting method | |
CN104851093A (en) | Vector surface data edge match detection method based on distance and angle control | |
CN105094051B (en) | The plane positioning compensation method of motion platform system | |
CN109766903A (en) | A kind of point cloud model SURFACES MATCHING method based on curved surface features | |
Shan et al. | Stereovision monitoring for entire collapse of a three‐story frame model under earthquake excitation | |
Yang et al. | Eccentricity error compensation for geometric camera calibration based on circular features | |
CN107436124A (en) | A kind of more stitch components positioning of view-based access control model and stitch error detection method | |
CN103500448B (en) | The affine Transform Model method for parameter estimation of high-density packages component | |
CN106595602B (en) | Relative orientation method based on homonymous line feature | |
CN109861859B (en) | Multi-Agent system fault detection method based on side inspection comprehensive judgment | |
Fu et al. | A flexible approach to light pen calibration for a monocular-vision-based coordinate measuring system | |
CN102564383B (en) | Method for determining interaxial angles of triaxial magnetic sensor based on axial surface angles | |
Sarkis et al. | A fast and robust solution to the five-pint relative pose problem using gauss-newton optimization on a manifold | |
Wu et al. | Noniterative calibration of a camera lens with radial distortion | |
CN109709467A (en) | A kind of automatic prober platform kinematic error compensation method | |
CN104751005A (en) | Flatness error evaluation method based on orthogonal experiment | |
Zhou et al. | Distortion correction using a single image based on projective invariability and separate model |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171205 |
|
WD01 | Invention patent application deemed withdrawn after publication |