CN105118086A - 3D point cloud data registering method and system in 3D-AOI device - Google Patents
3D point cloud data registering method and system in 3D-AOI device Download PDFInfo
- Publication number
- CN105118086A CN105118086A CN201510382095.2A CN201510382095A CN105118086A CN 105118086 A CN105118086 A CN 105118086A CN 201510382095 A CN201510382095 A CN 201510382095A CN 105118086 A CN105118086 A CN 105118086A
- Authority
- CN
- China
- Prior art keywords
- image
- translation
- matrix
- camera
- cloud data
- 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.)
- Granted
Links
Abstract
The invention relates to a 3D point cloud data registering method in 3D-AOI device. The method comprises the following steps: an internal matrix and a distortion parameter of a camera and a rotation matrix of an image are calculated; the movement interval for each time when the camera collects images is calculated according to the preset overlap width of adjacent images and the width of each image, and the image sequence is collected according to the movement interval; each image in the image sequence is subjected to correction and rotation; a translation matrix between adjacent images in the image sequence is calculated, the images are subjected to translation according to the translation matrix, a translation parameter is stored after translation, and a configuration file is formed; each image in the image sequence is subjected to splicing and fusion according to the configuration file and the preset overlap width, and a whole image is formed. By utilization of a calibration board which is used for correcting camera parameters originally, the high-precision characteristic is utilized repeatedly to correct errors of camera mechanical translation, therefore 2D data and 3D data are obtained to splice a required registering parameter, the splicing time of the whole image is shortened greatly, and the splicing precision is raised.
Description
Technical field
The present invention relates to AOI (AutomaticOpticInspection) apparatus field, particularly relate to the 3D cloud data method for registering in a kind of 3D-AOI equipment and system.
Background technology
The whole plate image of traditional AOI circuitry plate is form according to theoretical overlapping region direct splicing mostly.Image mosaic in traditional AOI equipment, the width of overlapping region is 0.Namely traditional image mosaic does not arrange theoretical overlapping region, and splicing does not have fusion steps.In order to ensure the precision of splicing, just high-precision motor and screw mandrel must be adopted, simultaneously also very high to the accuracy requirement of installing.This adds the holistic cost of equipment undoubtedly.
Meanwhile, due to the arrival of high-precision optical 3D technology, and due to the restriction of camera fields of view after configuration telecentric lens, in order to not make detection and the measuring accuracy of the error effect entirety of image and 3D Point-clouds Registration.Traditional image split-joint method in the urgent need to improve.In order to ensure higher accuracy of detection, constantly must correct the 2D image collected and the 3D data calculated in the process of circuit board being carried out to whole plate scanning, making it to overlap completely in theoretical overlapping region.
In traditional 3D Point-clouds Registration algorithm, mostly pursue to unknown visual angle have the cloud data of overlapping subset to carry out registration, splicing reconstructs 3D model, but at the most of data acquisition modes of industrial circle, there is certain rule.In existing industrial circle, 3D Point-clouds Registration technology is adopt " auxiliary point to ", i.e. Mark label on testee surface mount mostly, and strong angle point when splicing as data when the adjacent Point-clouds Registration obtained carries out registration.This method cannot realize the sampling and processing of large batch of 3D data.
Summary of the invention
Technical matters to be solved by this invention is, provides the 3D cloud data method for registering in a kind of 3D-AOI equipment and system, realizes 3D Point-clouds Registration and does not re-use " auxiliary point to ".The present invention is achieved in that
A 3D cloud data method for registering in 3D-AOI equipment, comprises the steps:
Steps A: gather piece image with camera from round dot scaling board, and utilize this image to calculate internal reference matrix and the distortion parameter of camera, and the rotation matrix of this image; Certain round dot center superposition in the center of this image and this image;
Step B: mobile interval each during width calculation collected by camera image according to the overlapping widths of the adjacent image preset and every piece image, and the image gathered by described mobile intervening sequences ground in described round dot scaling board, until the image acquisition in all regions is complete in described round dot scaling board, form image sequence;
Step C: according to described internal reference matrix, distortion parameter and rotation matrix to each width correct image and the rotation in described image sequence;
Step D: select a width as benchmark image from through the image sequence after overcorrect and rotation, and by its translation parameters zero setting; Meanwhile, calculate the translation matrix between adjacent two width images in the image sequence after overcorrect and rotation, and accordingly translation is carried out to each image in described image sequence, preserve the translation parameters of each image simultaneously, form configuration file;
Step e: splice according to described configuration file and described overlapping widths each image in described image sequence and merge, forms entire image.
Further, in described step D, translation matrix is:
N＝k*N
X+(1-k)*N
Y(0<k<1)；
Wherein k is weighting coefficient, and N is translation matrix, N
xfor the translation matrix of the image of X-direction, N
yfor the translation matrix of the image of Y direction, t
x, t '
xfor the translation pixel distance along X-axis, t
y, t '
yfor the translation pixel distance along Y-axis.
Further, described overlapping widths is less than the twice of the pixel distance between adjacent round dot center.
Further, also comprise the steps: to splice other images according to described configuration file and merge.
Further, in described step D, select the first width in described image sequence as benchmark image, translation is carried out to subsequent images; When carrying out translation to each image, with piece image before each image for benchmark, according to each image of translation matrix translation between each image and its front piece image.
A 3D cloud data registration arrangement in 3D-AOI equipment, comprising:
Camera calibration module, for gathering piece image by camera from round dot scaling board, and utilizes this image to calculate internal reference matrix and the distortion parameter of camera, and the rotation matrix of this image; Certain round dot center superposition in the center of this image and this image;
Image sequence acquisition module, for mobile interval each during width calculation collected by camera image according to the overlapping widths of the adjacent image preset and every piece image, and the image gathered by described mobile intervening sequences ground in described round dot scaling board, until the image acquisition in all regions is complete in described round dot scaling board, form image sequence;
Image correction module, for according to described internal reference matrix, distortion parameter and rotation matrix to each width correct image and the rotation in described image sequence;
Translation parameters configuration module, for selecting a width as benchmark image from the image sequence after overcorrect and rotation, and by its translation parameters zero setting; Meanwhile, calculate the translation matrix between adjacent two width images in the image sequence after overcorrect and rotation, and accordingly translation is carried out to each image in described image sequence, preserve the translation parameters of each image simultaneously, form configuration file;
Splicing Fusion Module, for splicing according to described configuration file and described overlapping widths each image in described image sequence and merge, forms entire image.
Further, in described translation parameters configuration module, translation matrix is:
N＝k*N
X+(1-k)*N
Y(0<k<1)；
Wherein k is weighting coefficient, and N is translation matrix, N
xfor the translation matrix of the image of X-direction, N
yfor the translation matrix of the image of Y direction, t
x, t '
xfor the translation pixel distance along X-axis, t
y, t '
yfor the translation pixel distance along Y-axis.
Further, described overlapping widths is less than the twice of the pixel distance between adjacent round dot center.
Further, described splicing Fusion Module is also for splice other images according to described configuration file and merge.
Further, in described translation parameters configuration module, select the first width in described image sequence as benchmark image, translation is carried out to subsequent images; When carrying out translation to each image, with piece image before each image for benchmark, according to each image of translation matrix translation between each image and its front piece image.
Compared with prior art, the present invention is by being originally only used to the scaling board correcting camera parameter, reuse the error of its high-precision feature for correcting camera Mechanical Moving, thus obtain 2D data and the registration parameter required for the splicing of 3D data, greatly reduce the whole plate image mosaic time, improve splicing precision.
Accompanying drawing explanation
Fig. 1: the 3D cloud data method for registering schematic flow sheet in the 3D-AOI equipment that the embodiment of the present invention provides;
Fig. 2: camera parameter demarcates gray level image used;
Fig. 3: single image initial point centre mark;
Fig. 4: image translation parameter sample calculation;
Fig. 5: the spliced whole plate image of scaling board;
Fig. 6: the 3D cloud data registration arrangement composition schematic diagram in the 3D-AOI equipment that the embodiment of the present invention provides.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.
3D-AOI device-specific is in carrying out 3D optical detection to circuit board.Fundamental purpose of the present invention is to provide the method for registering of 3D cloud data used in 3D-AOI equipment.Shown in Fig. 1, the 3D cloud data method for registering in the 3D-AOI equipment that the embodiment of the present invention provides comprises the steps:
Steps A: gather piece image with camera from round dot scaling board, and utilize this image to calculate internal reference matrix and the distortion parameter of camera, and the rotation matrix of this image; Certain round dot center superposition in the center of this image and this image.
Wherein, internal reference matrix: q=MQ,
Radial distortion:
Tangential distortion:
Rotation matrix:
Wherein q is the pixel coordinate of Circle in Digital Images dot center, and M is internal reference matrix, and Q is round dot world coordinates (actual coordinate), k
1, k
2, p
1, p
2, k
3for distortion parameter.X
corrected, y
correctedfor correcting rear coordinate, R
z(θ) be rotation matrix, θ is around the Z axis anglec of rotation.
Step B: mobile interval each during width calculation collected by camera image according to the overlapping widths of the adjacent image preset and every piece image, and the image gathered by mobile intervening sequences ground in round dot scaling board, until the image acquisition in all regions is complete in round dot scaling board, form image sequence.
Step C: according to internal reference matrix, distortion parameter and rotation matrix to each width correct image and the rotation in image sequence.
Step D: select a width as benchmark image from through the image sequence after overcorrect and rotation, and by its translation parameters zero setting; Meanwhile, calculate the translation matrix between adjacent two width images in the image sequence after overcorrect and rotation, and accordingly translation is carried out to each image in image sequence, preserve the translation parameters of each image simultaneously, form configuration file.In described step D, select the first width in described image sequence as benchmark image, translation is carried out to subsequent images; When carrying out translation to each image, with piece image before each image for benchmark, according to each image of translation matrix translation between each image and its front piece image.Translation matrix is:
N＝k*N
X+(1-k)*N
Y(0<k<1)。Wherein, k is weighting coefficient, and N is translation matrix, N
xfor the translation matrix of the image of X-direction, N
yfor the translation matrix of the image of Y direction, t
x, t '
xfor the translation pixel distance along X-axis, t
y, t '
yfor the translation pixel distance along Y-axis.
Step e: splice according to configuration file and overlapping widths each image in image sequence and merge, forms entire image.Obtained 2D image and the configuration file of scaling board to D by steps A.In actual applications, the 2D image of circuit board can directly correct according to configuration file, and carry out splicing and merging, corresponding 3D cloud data then can after calibration directly in sequence of computed images the image that physical location is adjacent cloud data in the difference in height average of overlapping region, then data along Z axis is moved to phase co-altitude, then splice after the overlapping region of 3D cloud data is merged.
A specific embodiment below for utilizing the present invention to carry out image mosaic:
The systematic error of first correcting camera before image registration.In steps A, the world coordinates of camera calibration is conveniently set, first gathers the image that in a round dot scaling board, certain round dot center overlaps with picture centre, gray-scale map as shown in Figure 2.The resolution of collected by camera image is 900*800, then the center point coordinate of the image of collected by camera is (450,400).Image center is set to true origin, the true origin of the round dot center pixel coordinate obtained after image procossing is moved to center point coordinate.And actual range between round dot is known, then the world coordinates value of corresponding circle dot center is the integral multiple of pixel distance (being 125 in Fig. 2) corresponding to this distance.Obtain pixel coordinate 35 according to Fig. 2, add corresponding world coordinates.The internal reference matrix of camera and distortion parameter and rotation matrix just can be obtained by general camera calibration method.
Step B and step C completes the correction of single picture in demarcation or actual application.Fig. 3 is single image initial point centre mark.The rough registration of view data is would have been completed when setting theoretical X, Y-axis overlapping widths when camera moves.On the AOI equipment of certain model, overlapping widths must be less than the twice of the pixel distance between adjacent round dot center, and this just ensures that overlapping region has and only has a row or column round dot for drawing translation matrix.Once have selected certain overlapping widths parameter, in follow-up use, this parameter is not modifiable.In this exemplary plot, X, Y-axis overlap are respectively 100 pixel distances, and namely overlapping widths is the width of 100 pixels.Using the initial point of first pictures as image registration in step S4, it is the initial point put in order to circuit board when the initial point of given camera Mechanical Moving and circuit board general image gather.
Step D realizes accuracy registration.In image sequence from initial point, according to acquisition order, the front piece image in every width image and image sequence has overlapping region.In Fig. 4, the upper left corner is image subject to registration, and figure below and right figure are the configuration image (" left figure " as herein described, " figure below " and " right figure " refer to upper left corner image, figure below and right figure in Fig. 4 respectively) in image sequence.For left images registration, in Fig. 4, in right figure, first obtain all complete round dots and pixel coordinate thereof by process.Remove and have default row or column, obtain a H
nrow W
nthe coordinate set of row.This coordinate set is:
{(x
ij,y
ij)|0≤j≤W
n-1,0≤i≤H
n-1}。
The coordinate choosing wherein row k calculates step-length X-direction step-length Wdx, the Y direction step-length Wdy of point coordinate of turning left from the right side.Wherein W
nfor:
If first row x
i0<100 (these 100 represent that the overlapping widths preset is the distance of 100 pixels), then directly preserve the angle point of first row data as coupling, otherwise predict by step-length left by first row data, until x
rtill <100, that is:
The angle point obtaining the coupling of right figure is thus:
{ (x
r, y
r) | 0≤r≤H
n-1}; Likely x in this column data
r<0.
The coordinate set that left side image subject to registration obtains is:
{(x′
ij,y′
ij)|0≤j≤W′
n-1,0≤i≤H′
n-1}。
Under last row coordinate points being moved to the coordinate system identical with right figure with formula (e).Step parameter Wdx ', Wdy ' substitute into formula (a) (b) by left figure coordinate set data and can be calculated.Formula (f) is used to find angle point in the right figure with registration nearest to arrange the angle point mated as left figure to the right again.
Angle point in left figure and right figure matches according to the mode of arest neighbors, obtains:
{(x
m,y
m,x′
m,y′
m)|0≤m≤min(H′
n,H
n)}。
Wherein, (x '
m, y '
m) ∈ { (x
l, y
l), (x
m, y
m) ∈ { (x
r, y
r).With right figure angle point for benchmark, left map migration parametric t can be calculated
x, t
y.
In like manner can calculate the migration parameter t ' of band registering images and figure below
x, t '
y.So finally try to achieve translation matrix:
N＝k*N
X+(1-k)*N
Y(0<k<1)。According to the translation matrix of trying to achieve by this correct image.
After the whole plate image rectification of all scaling boards, correction parameter is preserved into configuration file.Fig. 5 is the whole plate image of splicing after correcting, and pixel count is 16900*12700.Camera often moves after the gathered image that moves a step all corrected by steps A in actual applications, has corresponding translation parameters to correct.Namely the time of registration is eliminated when data are spliced.
As shown in Figure 6, based on above-mentioned bearing calibration, present invention also offers the 3D cloud data registration arrangement in a kind of 3D-AOI equipment.This system comprises camera calibration module 1, image sequence acquisition module 2, image correction module 3, translation parameters configuration module 4 and splicing Fusion Module 5.
Camera calibration module 1 for gathering piece image by camera from round dot scaling board, and utilizes this image to calculate internal reference matrix and the distortion parameter of camera, and the rotation matrix of this image; Certain round dot center superposition in the center of this image and this image.
Image sequence acquisition module 2 is for mobile interval each during width calculation collected by camera image according to the overlapping widths of the adjacent image preset and every piece image, and the image gathered by mobile intervening sequences ground in round dot scaling board, until the image acquisition in all regions is complete in round dot scaling board, form image sequence.
Image correction module 3 for according to internal reference matrix, distortion parameter and rotation matrix to each width correct image and the rotation in image sequence.
Translation parameters configuration module 4 is for selecting a width as benchmark image, and by its translation parameters zero setting from overcorrect and the image sequence after rotating; Meanwhile, calculate the translation matrix between adjacent two width images in the image sequence after overcorrect and rotation, and accordingly translation is carried out to each image in image sequence, preserve the translation parameters of each image simultaneously, form configuration file.Select the first width in described image sequence as benchmark image, translation is carried out to subsequent images; When carrying out translation to each image, with piece image before each image for benchmark, according to each image of translation matrix translation between each image and its front piece image.
Splicing Fusion Module 5, for splicing according to configuration file and overlapping widths each image in image sequence and merge, forms entire image.
In translation parameters configuration module 4, translation matrix is:
N＝k*N
X+(1-k)*N
Y(0<k<1)。Wherein k is weighting coefficient, and N is translation matrix, N
xfor the translation matrix of the image of X-direction, N
yfor the translation matrix of the image of Y direction, t
x, t '
xfor the translation pixel distance along X-axis, t
y, t '
yfor the translation pixel distance along Y-axis.
Described overlapping widths is less than the twice of the pixel distance between adjacent round dot center.In the present embodiment, overlapping widths is the width of 100 pixels.Splicing Fusion Module 5 is also for splice other images according to configuration file and merge.Data splicing is divided into two parts: first registration, merge again.Configuration file comprises the config files of X, Y-axis.Overlapping region is used to the direct fusion making view data (RGB), namely realizes the seamless spliced of view data.Because 2D view data only has X, Y-axis data, so data splicing directly can be realized.3D data (also known as altitude information or cloud data) have X, Y, Z tri-number of axle certificate, and the configuration file of storage can realize registration.The Z axis that overlapping region can be used to do view data merges, calculate the average height difference D of the overlapping region needing the two width images merged, the second width integral image is made to deduct D (being withdrawn into the sustained height with piece image by the second width image) again, and then directly merge with piece image, namely realize the seamless spliced of view data.This method corrects with image, and the configuration file drawn can be used for the splicing of 2D image, simultaneously for registration and the fusion of 3D data
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the 3D cloud data method for registering in 3D-AOI equipment, is characterized in that, comprise the steps:
Steps A: gather piece image with camera from round dot scaling board, and utilize this image to calculate internal reference matrix and the distortion parameter of camera, and the rotation matrix of this image; Certain round dot center superposition in the center of this image and this image;
Step B: mobile interval each during width calculation collected by camera image according to the overlapping widths of the adjacent image preset and every piece image, and the image gathered by described mobile intervening sequences ground in described round dot scaling board, until the image acquisition in all regions is complete in described round dot scaling board, form image sequence;
Step C: according to described internal reference matrix, distortion parameter and rotation matrix to each width correct image and the rotation in described image sequence;
Step D: select a width as benchmark image from through the image sequence after overcorrect and rotation, and by its translation parameters zero setting; Meanwhile, calculate the translation matrix between adjacent two width images in the image sequence after overcorrect and rotation, and accordingly translation is carried out to each image in described image sequence, preserve the translation parameters of each image simultaneously, form configuration file;
Step e: splice according to described configuration file and described overlapping widths each image in described image sequence and merge, forms entire image.
2. the 3D cloud data method for registering in 3D-AOI equipment as claimed in claim 1, it is characterized in that, in described step D, translation matrix is:
N＝k*N
X+(1-k)*N
Y(0<k<1)；
Wherein k is weighting coefficient, and N is translation matrix, N
xfor the translation matrix of the image of X-direction, N
yfor the translation matrix of the image of Y direction, t
x, t '
xfor the translation pixel distance along X-axis, t
y, t '
yfor the translation pixel distance along Y-axis.
3. the 3D cloud data method for registering in 3D-AOI equipment as claimed in claim 1, it is characterized in that, described overlapping widths is less than the twice of the pixel distance between adjacent round dot center.
4. the 3D cloud data method for registering in 3D-AOI equipment as claimed in claim 1, is characterized in that, also comprises the steps: to splice other images according to described configuration file and merge.
5. the 3D cloud data method for registering in 3D-AOI equipment as claimed in claim 1, is characterized in that, in described step D, selects the first width in described image sequence as benchmark image, carries out translation to subsequent images; When carrying out translation to each image, with piece image before each image for benchmark, according to each image of translation matrix translation between each image and its front piece image.
6. the 3D cloud data registration arrangement in 3D-AOI equipment, is characterized in that, comprising:
Camera calibration module, for gathering piece image by camera from round dot scaling board, and utilizes this image to calculate internal reference matrix and the distortion parameter of camera, and the rotation matrix of this image; Certain round dot center superposition in the center of this image and this image;
Image sequence acquisition module, for mobile interval each during width calculation collected by camera image according to the overlapping widths of the adjacent image preset and every piece image, and the image gathered by described mobile intervening sequences ground in described round dot scaling board, until the image acquisition in all regions is complete in described round dot scaling board, form image sequence;
Image correction module, for according to described internal reference matrix, distortion parameter and rotation matrix to each width correct image and the rotation in described image sequence;
Translation parameters configuration module, for selecting a width as benchmark image from the image sequence after overcorrect and rotation, and by its translation parameters zero setting; Meanwhile, calculate the translation matrix between adjacent two width images in the image sequence after overcorrect and rotation, and accordingly translation is carried out to each image in described image sequence, preserve the translation parameters of each image simultaneously, form configuration file;
Splicing Fusion Module, for splicing according to described configuration file and described overlapping widths each image in described image sequence and merge, forms entire image.
7. the 3D cloud data registration arrangement in 3D-AOI equipment as claimed in claim 6, it is characterized in that, in described translation parameters configuration module, translation matrix is:
N＝k*N
X+(1-k)*N
Y(0<k<1)；
Wherein k is weighting coefficient, and N is translation matrix, N
xfor the translation matrix of the image of X-direction, N
yfor the translation matrix of the image of Y direction, t
x, t '
xfor the translation pixel distance along X-axis, t
y, t '
yfor the translation pixel distance along Y-axis.
8. the 3D cloud data registration arrangement in 3D-AOI equipment as claimed in claim 6, it is characterized in that, described overlapping widths is less than the twice of the pixel distance between adjacent round dot center.
9. the 3D cloud data registration arrangement in 3D-AOI equipment as claimed in claim 6, is characterized in that, described splicing Fusion Module is also for splice other images according to described configuration file and merge.
10. the 3D cloud data registration arrangement in 3D-AOI equipment as claimed in claim 6, is characterized in that, in described translation parameters configuration module, selects the first width in described image sequence as benchmark image, carries out translation to subsequent images; When carrying out translation to each image, with piece image before each image for benchmark, according to each image of translation matrix translation between each image and its front piece image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510382095.2A CN105118086B (en) | 2015-06-30 | 2015-06-30 | 3D point cloud Registration of Measuring Data method and system in 3D AOI equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510382095.2A CN105118086B (en) | 2015-06-30 | 2015-06-30 | 3D point cloud Registration of Measuring Data method and system in 3D AOI equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105118086A true CN105118086A (en) | 2015-12-02 |
| CN105118086B CN105118086B (en) | 2017-09-29 |
Family
ID=54666059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510382095.2A Active CN105118086B (en) | 2015-06-30 | 2015-06-30 | 3D point cloud Registration of Measuring Data method and system in 3D AOI equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105118086B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017107564A1 (en) * | 2015-12-23 | 2017-06-29 | 广州视源电子科技股份有限公司 | Board image acquisition method and system |
| CN109031339A (en) * | 2018-05-23 | 2018-12-18 | 北京控制工程研究所 | A kind of three-dimensional point cloud motion compensation process |
| CN109345597A (en) * | 2018-09-27 | 2019-02-15 | 四川大学 | A kind of camera calibration image-pickup method and device based on augmented reality |
| CN109509226A (en) * | 2018-11-27 | 2019-03-22 | 广东工业大学 | Three dimensional point cloud method for registering, device, equipment and readable storage medium storing program for executing |
| CN110298799A (en) * | 2019-06-25 | 2019-10-01 | 福建工程学院 | A kind of PCB image positioning correction method |
| CN111982015A (en) * | 2020-08-18 | 2020-11-24 | 深圳大学 | Method for monitoring structure geometry |
| CN112286972A (en) * | 2020-11-06 | 2021-01-29 | 精华电子(苏州)有限公司 | AOI tracing system |
| CN112750169A (en) * | 2021-01-13 | 2021-05-04 | 深圳瀚维智能医疗科技有限公司 | Camera calibration method, device and system and computer readable storage medium |
| CN114638824A (en) * | 2022-05-11 | 2022-06-17 | 成都数联云算科技有限公司 | Fusion method, device, equipment and medium for collecting images based on AOI equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5341439A (en) * | 1989-09-21 | 1994-08-23 | Hsu Shin Yi | System for texture-based automatic detection of man-made objects in representations of sensed natural environmental scenes |
| CN101276465A (en) * | 2008-04-17 | 2008-10-01 | 上海交通大学 | Method for automatically split-jointing wide-angle image |
| CN101710932A (en) * | 2009-12-21 | 2010-05-19 | 深圳华为通信技术有限公司 | Image stitching method and device |
-
2015
- 2015-06-30 CN CN201510382095.2A patent/CN105118086B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5341439A (en) * | 1989-09-21 | 1994-08-23 | Hsu Shin Yi | System for texture-based automatic detection of man-made objects in representations of sensed natural environmental scenes |
| CN101276465A (en) * | 2008-04-17 | 2008-10-01 | 上海交通大学 | Method for automatically split-jointing wide-angle image |
| CN101710932A (en) * | 2009-12-21 | 2010-05-19 | 深圳华为通信技术有限公司 | Image stitching method and device |
Non-Patent Citations (1)
| Title |
|---|
| 林柱杰等: "基于AOI检测系统的图像拼接技术", 《佛山科学技术学院学报(自然科学版)》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017107564A1 (en) * | 2015-12-23 | 2017-06-29 | 广州视源电子科技股份有限公司 | Board image acquisition method and system |
| CN109031339A (en) * | 2018-05-23 | 2018-12-18 | 北京控制工程研究所 | A kind of three-dimensional point cloud motion compensation process |
| CN109031339B (en) * | 2018-05-23 | 2020-11-10 | 北京控制工程研究所 | Three-dimensional point cloud motion compensation method |
| CN109345597A (en) * | 2018-09-27 | 2019-02-15 | 四川大学 | A kind of camera calibration image-pickup method and device based on augmented reality |
| CN109345597B (en) * | 2018-09-27 | 2020-08-25 | 四川大学 | Camera calibration image acquisition method and device based on augmented reality |
| CN109509226B (en) * | 2018-11-27 | 2023-03-28 | 广东工业大学 | Three-dimensional point cloud data registration method, device and equipment and readable storage medium |
| CN109509226A (en) * | 2018-11-27 | 2019-03-22 | 广东工业大学 | Three dimensional point cloud method for registering, device, equipment and readable storage medium storing program for executing |
| CN110298799A (en) * | 2019-06-25 | 2019-10-01 | 福建工程学院 | A kind of PCB image positioning correction method |
| CN110298799B (en) * | 2019-06-25 | 2021-02-23 | 福建工程学院 | PCB image positioning correction method |
| CN111982015A (en) * | 2020-08-18 | 2020-11-24 | 深圳大学 | Method for monitoring structure geometry |
| CN112286972A (en) * | 2020-11-06 | 2021-01-29 | 精华电子(苏州)有限公司 | AOI tracing system |
| CN112286972B (en) * | 2020-11-06 | 2024-02-20 | 精华电子(苏州)有限公司 | AOI tracing system |
| CN112750169A (en) * | 2021-01-13 | 2021-05-04 | 深圳瀚维智能医疗科技有限公司 | Camera calibration method, device and system and computer readable storage medium |
| CN112750169B (en) * | 2021-01-13 | 2024-03-19 | 深圳瀚维智能医疗科技有限公司 | Camera calibration method, device, system and computer readable storage medium |
| CN114638824A (en) * | 2022-05-11 | 2022-06-17 | 成都数联云算科技有限公司 | Fusion method, device, equipment and medium for collecting images based on AOI equipment |
| CN114638824B (en) * | 2022-05-11 | 2022-08-23 | 成都数联云算科技有限公司 | Fusion method, device, equipment and medium for collecting images based on AOI equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105118086B (en) | 2017-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105118086A (en) | 3D point cloud data registering method and system in 3D-AOI device | |
| CN110211043B (en) | Registration method based on grid optimization for panoramic image stitching | |
| CN102376089B (en) | Target correction method and system | |
| CN107993263B (en) | Automatic calibration method for panoramic system, automobile, calibration device and storage medium | |
| CN111815719B (en) | External parameter calibration method, device and equipment of image acquisition equipment and storage medium | |
| CN105716542B (en) | A kind of three-dimensional data joining method based on flexible characteristic point | |
| CN109272574B (en) | Construction method and calibration method of linear array rotary scanning camera imaging model based on projection transformation | |
| CN102768762B (en) | Digital camera calibration method targeted to shield tunnel defect digital radiography detection and device thereof | |
| WO2021004416A1 (en) | Method and apparatus for establishing beacon map on basis of visual beacons | |
| CN103729841B (en) | A kind of based on side's target model and the camera distortion bearing calibration of perspective projection | |
| CN104089628B (en) | Self-adaption geometric calibration method of light field camera | |
| CN103150724B (en) | Segmented model-based camera calibration method | |
| CN110443879B (en) | Perspective error compensation method based on neural network | |
| CN103473771A (en) | Method for calibrating camera | |
| CN105118021A (en) | Feature point-based image registering method and system | |
| CN108716890A (en) | A kind of high-precision size detecting method based on machine vision | |
| CN111872544B (en) | Calibration method and device for laser light-emitting indication point and galvanometer coaxial vision system | |
| CN113920205B (en) | Calibration method of non-coaxial camera | |
| CN105118042A (en) | Aligned adhering method and device | |
| Ding et al. | A robust detection method of control points for calibration and measurement with defocused images | |
| CN104167001A (en) | Large-visual-field camera calibration method based on orthogonal compensation | |
| CN105405135B (en) | Two-step method photography object point, picture point automatic matching method based on basic configuration point | |
| CN108961187B (en) | Label cambered surface image correction method | |
| CN113793266A (en) | Multi-view machine vision image splicing method, system and storage medium | |
| CN116958218A (en) | Point cloud and image registration method and equipment based on calibration plate corner alignment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 523000 Second Floor, Executive Building No. 1 Minxing Road, Chang'an Town Corner Community, Dongguan City, Guangdong Province Patentee after: Dongguan Meng Tuo Intelligent Technology Co., Ltd. Address before: 523000 4th Floor, 118 Guanchang Road, Yongtou, Chang'an Town, Dongguan City, Guangdong Province Patentee before: Dongguan MENTO Photoelectric Technology Co., Ltd. |