CN110533589A - A kind of threedimensional model joining method based on zoom micro-image sequence - Google Patents
A kind of threedimensional model joining method based on zoom micro-image sequence Download PDFInfo
- Publication number
- CN110533589A CN110533589A CN201910648208.7A CN201910648208A CN110533589A CN 110533589 A CN110533589 A CN 110533589A CN 201910648208 A CN201910648208 A CN 201910648208A CN 110533589 A CN110533589 A CN 110533589A
- Authority
- CN
- China
- Prior art keywords
- threedimensional model
- model
- image
- threedimensional
- dimensional
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000002156 mixing Methods 0.000 claims abstract description 31
- 230000000007 visual effect Effects 0.000 claims abstract description 22
- 238000013519 translation Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 13
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 230000009466 transformation Effects 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 claims description 3
- 238000004441 surface measurement Methods 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 abstract 1
- 238000000691 measurement method Methods 0.000 description 10
- 238000011160 research Methods 0.000 description 5
- 238000012876 topography Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 230000006378 damage Effects 0.000 description 2
- 238000005305 interferometry Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000004626 scanning electron microscopy Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of threedimensional model joining methods based on zoom micro-image sequence, specific step is as follows: obtaining the zoom micro-image sequence under the more visuals field of object under test, by focusing evaluation algorithms 2 d texture blending image and corresponding threedimensional model, Feature Points Matching is carried out to lap two dimensional image using the matching algorithm between two dimensional image, obtains the match point between two dimensional image.Two-dimentional match point is corresponded on threedimensional model later, the matching double points between threedimensional model, the transformation matrix between seeking threedimensional model is obtained, and rotation translation transformation is carried out to threedimensional model to be spliced, realizes the splicing between threedimensional model.This method can realize the big visual field of measured object, 360 degree of omnidirections and cross-scale surface measurement, and generate three-dimensional panoramic model, and measurement accuracy is high, and speed is fast, high degree of automation.
Description
Technical field
The present invention relates to a kind of threedimensional model joining methods based on zoom micro-image sequence, belong to non-contact microcosmic table
Face three-dimensional measurement technology.
Background technique
The high-acruracy survey of object micromorphology is an important research direction of fields of measurement, belongs to micro/nano-scale
On measurement method, this method can be applied to include precision engineering, micro manufacturing, quality testing, biotechnology, clinical medicine etc. side
The numerous areas in face.
The measurement method of object micromorphology is divided into contact measurement method and contactless measurement two major classes.
The shortcomings that surface topography measurement method compared to contact is easy to damage measured workpiece surface, contactless surface topography
Learning measurement method is mainstream measurement method in the field, just towards speed faster, resolution ratio is higher, measurement range is higher, suitable
Developed with the wider array of direction of range.In contactless surface topography measurement method, zoom micrometering is compared to laser
Phase-shifting interferometry, scanning white light interferometry, position from defocus method, confocal micro-measurement method, scanning electron microscopy measurement method etc. its
His several contactless measurements have apparent technical advantage, such as measurement accuracy is high, measurement rapidly and efficiently, be suitble to measurement tool
There are surface, the strong robustness etc. of high inclination-angle.
Zoom micrometering is a kind of relatively new surface topography measuring method, and three-dimensional model reconfiguration and threedimensional model are spelled
Researching value with higher is connect, domestic some research institutions and company are being dedicated to the research of the technology at present, existing
The more reconstruct for resting on threedimensional model under two dimensional image fusion and haplopia open country of research work, for more field of view three-dimensional model splicings
Algorithm excavate and improve insufficient.
Model splicing method is the critical issue of three-dimensional measurement technology, and the precision of splicing will affect the quality of Model Reconstruction,
The speed of splicing will affect the actual effect of actual application.
Summary of the invention
For the problems of above-mentioned prior art, the purpose of the present invention is to propose to one kind to be based on zoom micro-image sequence
The threedimensional model joining method of column, this method are based on zoom micro-image sequence, and combine and focus evaluation method and translation rotation
The threedimensional model stitching measure method of platform.
In order to achieve the above objectives, the present invention adopts the following technical scheme:
A kind of threedimensional model joining method based on zoom micro-image sequence, comprising the following steps:
S1, the 2 d texture image and its corresponding three-dimensional model for obtaining measured object under haplopia open country: acquisition measured object list first
Zoom micro-image sequence under the visual field is focused testee surface zoom image sequence using focusing evaluation method and comments
Valence calculates, and 2 d texture blending image and threedimensional model under the visual field is obtained, as reference picture and threedimensional model;
S2, the shape feature according to measured object, rotation or translation rotation translation platform, obtain the visual field after rotation or translation
Under zoom micro-image sequence, obtain the 2 d texture blending image and its corresponding three in the visual field in conjunction with evaluation method is focused
Dimension module, as image and threedimensional model to be spliced;
S3,2 d texture blending image matching double points acquisition;
The registration of S4, threedimensional model;
The splicing of S5, more field of view three-dimensional models.
Compared with prior art, the invention has the benefit that
The present invention, which combines, focuses evaluation method and rotation translation platform method, proposes a kind of based on 2 d texture blending image
The threedimensional model joining method of registration, improves the research of zoom micrometering technology.This method precision is high, speed it is fast, it can be achieved that
The big visual field, 360 degree and across nanoscale object surface measurement.Compared with the contact measurement methods such as three coordinate measuring machine, this method at
This is low, and the injuries such as abrasion, scratch will not be caused to measured object surface.In addition this method is used is registrated based on 2 d texture image
It realizes threedimensional model splicing, the initial matching of characteristic point is completed in 2 d texture blending image, and gone using consistency algorithm
It except Mismatching point pair, corresponds on threedimensional model, obtains high accuracy three-dimensional Model Matching point pair, it is quick to model realization, smart
Really splice, improves splicing efficiency and precision.
Detailed description of the invention
Fig. 1 is the overall flow figure of the method for the present invention;
Fig. 2 is Alicona calibrated bolck, and Triangle Model is the part for experiment;
Fig. 3 a is the left-half image sequence of Triangle Model, and 3b is the right half part image sequence of Triangle Model;
Fig. 4 a is the corresponding two-dimentional blending image of Fig. 3 a and threedimensional model, and 4b is the corresponding two-dimentional blending image of 3b and three-dimensional
Model;
Fig. 5 is the feature point extraction and registration of 2 d texture blending image;
Fig. 6 is the splicing of threedimensional model.
Specific embodiment
With reference to the accompanying drawing, specific embodiments of the present invention are described further.
As shown in Figure 1, a kind of threedimensional model joining method based on zoom micro-image sequence, comprising the following steps:
S1, the 2 d texture image and its corresponding three-dimensional model for obtaining measured object under haplopia open country.Obtaining measured object first should
Zoom micro-image sequence under the visual field is focused testee surface zoom image sequence using focusing assessment technique and comments
Valence, which calculates, obtains 2 d texture blending image and threedimensional model under the visual field, as reference picture and threedimensional model.
S2, the shape feature according to measured object, rotation or translation rotation translation platform, obtain zoom micro-image sequence,
In conjunction with the 2 d texture blending image and its corresponding three for focusing another visual field of assessment technique acquisition (there is lap with S1)
Dimension module, as image and threedimensional model to be spliced.
S3,2 d texture blending image matching double points acquisition, comprising the following steps:
Characteristic point detection between S31,2 d texture blending image, using point feature extraction algorithm to obtaining in step S1
Characteristic point detection is carried out with reference to 2 d texture blending image to be spliced is obtained in 2 d texture image and step S2.
S32,2 d texture blending image characteristic point slightly match, using K dimension (K-D) tree similarity measurements quantity algorithm to step
The 2 d texture image characteristic point obtained in S31 is matched, and potential matching double points are obtained.
Essence matching between S33, two dimensional image is obtained potential using random consistency (RANSAC) algorithm removal step S32
The Mismatching point of matching double points obtains the accurate matching double points of 2 d texture blending image part.
The registration of S4, threedimensional model, comprising the following steps:
S41, threedimensional model feature point pair matching correspond to corresponding three-dimensional mould using matching double points are obtained in step S33
In type, the matching double points of two threedimensional models, { p ' are obtainediAnd { pi}。
The rough registration of S42, threedimensional model, the threedimensional model matching double points { p ' that step S41 is obtainediAnd { piAs defeated
Enter, seek the transformation matrix between model and reference model subject to registration using least square method, and model is coordinately transformed,
The error for seeking reference model and transformation model lap, specifically includes:
S421, least square method seek spin matrix R and translation matrix T between reference model and model to be spliced, make
It is minimum to obtain formula (1) square-error:
∑2=| | p 'i-(Rp+T)||2 (1)
S422, Singular-value Decomposition Solution R calculate threedimensional model matching double points { p 'iAnd { piMass center { q 'iAnd { qi};
S423, calculatingAnd singular value decomposition is carried out to H, such as formula (2),
H=U Λ VT (2)
S424, X=VU is calculatedT, so that R=X, T=p '-Rp.
S425, Model Matching to be spliced point coordinate transform,
The essence registration of S43, threedimensional model, set error threshold, by transformed Model Matching pointAs new subject to registration
Model three-dimensional match point is iterated according to step S42 and seeks new transformation matrix and error.When error is less than the threshold of setting
Value stops iteration, model to be spliced is coordinately transformed, and obtains accurately split-join model.
The splicing of S5, more field of view three-dimensional models, comprising the following steps:
S51, step S43 is obtained into split-join model as new reference model, according to the shape feature of measured object, rotation or
Translation rotation translation platform, obtains the zoom micro-image sequence under the visual field, obtains another visual field in conjunction with assessment technique is focused
(with step S2 obtain 2 d texture blending image have lap) two dimensional image and its corresponding threedimensional model, as to
The two dimensional image and threedimensional model of splicing.
S52, step S2 acquisition 2 d texture blending image is merged into figure with the step S51 2 d texture for obtaining another visual field
Picture repeats step S3, obtains the matching double points of two images.
S53, due to the corresponding threedimensional model of blending image two-dimentional in step S2 with blending image two-dimentional in step S1
Corresponding threedimensional model is spliced into new threedimensional model, then needing to obtain two-dimentional matching double points in step S52 corresponds to step
Rapid S43 obtains the threedimensional model to be spliced obtained in splicing threedimensional model and step S51, obtains three-dimensional of two threedimensional models
With point pair, step S4 is repeated, obtains three-dimensional splicing model.
S53, the threedimensional model that step S51 to step S53 are repeated under the multiple visuals field of measured object is spliced to the same coordinate system
Under, obtain the complete threedimensional model of measured object tested region.
This method is to Alicona calibrated bolck intermediate cam model, as shown in Fig. 2, shooting obtains Triangle Model with weight respectively
The zoom micro-image sequence at two visual angles of folded part, as best shown in figures 3 a and 3b.
Fig. 4 a is to be focused the two dimension that evaluation obtains to zoom micro-image sequence in Fig. 3 a by focusing evaluation algorithms
Merge texture image and threedimensional model.Fig. 4 b is commented by focusing to evaluate to calculate to be focused zoom micro-image sequence in such as 3b
The two dimension fusion texture image and threedimensional model that valence obtains.
Fig. 5 is to carry out feature point extraction and Characteristic points match to two dimension fusion texture image, firstly, carrying out to two images
Characteristic point detection, recycling K dimension (K-D) tree similarity measurements quantity algorithm two-dimensional texture map are matched as characteristic point, are obtained potential
Matching double points, finally remove the Mismatching points of potential matching double points using random consistency (RANSAC) algorithm, obtain two dimension
The accurate matching double points of grain table image part, totally 503 pairs.By corresponding to two-dimentional matching double points on threedimensional model, by most
Small square law calculates spin matrix and translation matrix, and step-up error threshold value is 0.8, obtains spin matrix R=by an iteration
[9.99999743e-01 -4.92118183e-04 5.21967004e-04;4.93984973e-04 9.99993461e-01-
3.58237426e-03;- 5.20200639e-04 3.58263118e-03 9.99993447e-01], translation matrix T=[-
28.96219433;390.70618568;- 5.65861005], obtaining transformed error is 0.63558948.
Fig. 6 is two visual angle 3-D images of split-join model, and model to be spliced is coordinately transformed rear and reference model
Splicing is under the same coordinate system.
Claims (5)
1. a kind of threedimensional model joining method based on zoom micro-image sequence, which comprises the following steps:
S1, the 2 d texture image and its corresponding three-dimensional model for obtaining measured object under haplopia open country: acquisition measured object haplopia first is wild
Under zoom micro-image sequence, using focus evaluation method to testee surface zoom image sequence be focused evaluation meter
It calculates, 2 d texture blending image and threedimensional model under the visual field is obtained, as reference picture and threedimensional model;
S2, the shape feature according to measured object, rotation or translation rotation translation platform, after acquisition rotation or translation under the visual field
Zoom micro-image sequence, in conjunction with focus evaluation method obtain the visual field 2 d texture blending image and its corresponding three-dimensional mould
Type, as image and threedimensional model to be spliced;
S3,2 d texture blending image matching double points acquisition;
The registration of S4, threedimensional model;
The splicing of S5, more field of view three-dimensional models.
2. the threedimensional model joining method according to claim 1 based on zoom micro-image sequence, which is characterized in that institute
State step S3 specifically includes the following steps:
Characteristic point detection between S31,2 d texture blending image, the reference using point feature extraction algorithm to being obtained in step S1
2 d texture blending image progress characteristic point detection to be spliced is obtained in 2 d texture image and step S2;
S32,2 d texture blending image characteristic point slightly match, using K dimension (K-D) tree similarity measurements quantity algorithm in step S31
The 2 d texture image characteristic point of acquisition is matched, and potential matching double points are obtained;
Essence matching between S33, two dimensional image obtains potential match point using random consistency RANSAC algorithm removal step S32
Pair Mismatching point, obtain the accurate matching double points of 2 d texture blending image part.
3. the threedimensional model joining method according to claim 1 based on zoom micro-image sequence, which is characterized in that institute
State step S4 specifically includes the following steps:
S41, threedimensional model feature point pair matching are corresponded on corresponding threedimensional model using matching double points are obtained in step S33,
Obtain the matching double points of two threedimensional models, { p 'iAnd { pi};
The rough registration of S42, threedimensional model, the threedimensional model matching double points { p ' that step S41 is obtainediAnd { piAs input, benefit
The transformation matrix between model and reference model subject to registration is sought with least square method, and model is coordinately transformed, is sought
The error of reference model and transformation model lap;
The essence registration of S43, threedimensional model, set error threshold, by transformed Model Matching pointAs new model subject to registration
Three-dimensional match point is iterated according to step S42 and seeks new transformation matrix and error;When threshold value of the error less than setting, stop
Model to be spliced is coordinately transformed by only iteration, obtains accurately split-join model.
4. the threedimensional model joining method according to claim 3 based on zoom micro-image sequence, which is characterized in that institute
State step S42 specifically includes the following steps:
S421, least square method seek spin matrix R and translation matrix T between reference model and model to be spliced, so that formula
(1) square-error is minimum:
∑2=| | p 'i-(Rp+T)||2 (1)
S422, Singular-value Decomposition Solution R calculate threedimensional model matching double points { p 'iAnd { piMass center { q 'iAnd { qi};
S423, calculatingAnd singular value decomposition is carried out to H, such as formula (2),
H=U Λ VT (2)
S424, X=VU is calculatedT, so that R=X, T=p '-Rp;
S425, Model Matching to be spliced point coordinate transform,
5. the threedimensional model joining method according to claim 1 based on zoom micro-image sequence, which is characterized in that institute
State step S5 specifically includes the following steps:
S51, step S43 is obtained to split-join model as new reference model, according to the shape feature of measured object, rotation or translation
Rotation translation platform, obtains micro-image sequence, and the two dimensional image and its correspondence in another visual field are obtained in conjunction with focusing evaluation method
Threedimensional model, as two dimensional image and threedimensional model to be spliced;
S52, step S2 is obtained to the 2 d texture blending image that 2 d texture blending image obtains another visual field with step S51,
Step S3 is repeated, the matching double points of two images are obtained;
S53, due to the corresponding threedimensional model of blending image two-dimentional in step S2 it is corresponding with blending image two-dimentional in step S1
Threedimensional model be spliced into new threedimensional model, correspond to step S43 then needing that two-dimentional matching double points will be obtained in step S52
The threedimensional model to be spliced obtained in splicing threedimensional model and step S51 is obtained, the three-dimensional match point of two threedimensional models is obtained
It is right, step S4 is repeated, three-dimensional splicing model is obtained;
S53, the threedimensional model for repeating step S51 to step S53 under the multiple visuals field of measured object is spliced under the same coordinate system, is obtained
Obtain the complete threedimensional model of measured object tested region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910648208.7A CN110533589A (en) | 2019-07-18 | 2019-07-18 | A kind of threedimensional model joining method based on zoom micro-image sequence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910648208.7A CN110533589A (en) | 2019-07-18 | 2019-07-18 | A kind of threedimensional model joining method based on zoom micro-image sequence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110533589A true CN110533589A (en) | 2019-12-03 |
Family
ID=68660573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910648208.7A Pending CN110533589A (en) | 2019-07-18 | 2019-07-18 | A kind of threedimensional model joining method based on zoom micro-image sequence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110533589A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113052835A (en) * | 2021-04-20 | 2021-06-29 | 江苏迅捷装具科技有限公司 | Medicine box detection method and detection system based on three-dimensional point cloud and image data fusion |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103049896A (en) * | 2012-12-27 | 2013-04-17 | 浙江大学 | Automatic registration algorithm for geometric data and texture data of three-dimensional model |
CN104392426A (en) * | 2014-10-23 | 2015-03-04 | 华中科技大学 | Adaptive markerless three-dimensional point cloud automatic registration method |
CN104807494A (en) * | 2015-04-28 | 2015-07-29 | 上海大学 | Object micro surface morphology optical five-degree-of-freedom measurement device and method |
CN105825518A (en) * | 2016-03-31 | 2016-08-03 | 西安电子科技大学 | Sequence image rapid three-dimensional reconstruction method based on mobile platform shooting |
CN106960442A (en) * | 2017-03-01 | 2017-07-18 | 东华大学 | Based on the infrared night robot vision wide view-field three-D construction method of monocular |
CN107240067A (en) * | 2017-05-11 | 2017-10-10 | 同济大学 | A kind of sequence image method for automatically split-jointing based on three-dimensional reconstruction |
-
2019
- 2019-07-18 CN CN201910648208.7A patent/CN110533589A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103049896A (en) * | 2012-12-27 | 2013-04-17 | 浙江大学 | Automatic registration algorithm for geometric data and texture data of three-dimensional model |
CN104392426A (en) * | 2014-10-23 | 2015-03-04 | 华中科技大学 | Adaptive markerless three-dimensional point cloud automatic registration method |
CN104807494A (en) * | 2015-04-28 | 2015-07-29 | 上海大学 | Object micro surface morphology optical five-degree-of-freedom measurement device and method |
CN105825518A (en) * | 2016-03-31 | 2016-08-03 | 西安电子科技大学 | Sequence image rapid three-dimensional reconstruction method based on mobile platform shooting |
CN106960442A (en) * | 2017-03-01 | 2017-07-18 | 东华大学 | Based on the infrared night robot vision wide view-field three-D construction method of monocular |
CN107240067A (en) * | 2017-05-11 | 2017-10-10 | 同济大学 | A kind of sequence image method for automatically split-jointing based on three-dimensional reconstruction |
Non-Patent Citations (3)
Title |
---|
史艳琼等: "变焦显微成像三维测量算法性能分析" * |
史艳琼等: "变焦显微成像三维测量算法性能分析", 《激光与光电子学进展》 * |
胡笑莉等: "基于立体视觉的三维立体模型全自动拼接方法", 《科学技术与工程》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113052835A (en) * | 2021-04-20 | 2021-06-29 | 江苏迅捷装具科技有限公司 | Medicine box detection method and detection system based on three-dimensional point cloud and image data fusion |
CN113052835B (en) * | 2021-04-20 | 2024-02-27 | 江苏迅捷装具科技有限公司 | Medicine box detection method and system based on three-dimensional point cloud and image data fusion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20240037765A1 (en) | High-precision dynamic real-time 360-degree omnidirectional point cloud acquisition method based on fringe projection | |
CN105783775B (en) | A kind of minute surface and class minute surface object surface appearance measuring device and method | |
Li et al. | Whole-field thickness strain measurement using multiple camera digital image correlation system | |
Weckenmann et al. | Multisensor data fusion in dimensional metrology | |
Zhou et al. | Complete calibration of a structured light stripe vision sensor through planar target of unknown orientations | |
US8803943B2 (en) | Formation apparatus using digital image correlation | |
Wu et al. | A novel high precise laser 3D profile scanning method with flexible calibration | |
CN106568394A (en) | Hand-held three-dimensional real-time scanning method | |
Zhou et al. | Constructing feature points for calibrating a structured light vision sensor by viewing a plane from unknown orientations | |
CN111353997B (en) | Real-time three-dimensional surface defect detection method based on fringe projection | |
Jiang et al. | Combined shape measurement based on locating and tracking of an optical scanner | |
Jia et al. | A field measurement method for large objects based on a multi-view stereo vision system | |
CN116402792A (en) | Space hole site butt joint method based on three-dimensional point cloud | |
Hu et al. | Calibration and rectification of bi-telecentric lenses in Scheimpflug condition | |
CN111028280A (en) | # -shaped structured light camera system and method for performing scaled three-dimensional reconstruction of target | |
CN110533589A (en) | A kind of threedimensional model joining method based on zoom micro-image sequence | |
CN112747671B (en) | Three-dimensional detection system and three-dimensional detection method | |
Chen et al. | A novel mirrored binocular vision sensor based on spherical catadioptric mirrors | |
He et al. | Deployment of a deep-learning based multi-view stereo approach for measurement of ship shell plates | |
Wang et al. | A direct calibration method for line structured light measurement system based on parallel lines | |
Wang | Disparity surface reconstruction based on a stereo light microscope and laser fringes | |
CN104134206A (en) | CT body data fast matching method based on three-dimensional binary feature descriptors | |
CN110260817B (en) | Complex surface deflection measurement self-positioning method based on virtual mark points | |
CN207816206U (en) | Based on the microscopical three-dimensional surface topography instrument of mating plate | |
Qian et al. | Fast 3D surface defect detection with fringe projection |
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: 20191203 |