CN109840934A - A kind of the threedimensional model generation method and system of workpiece - Google Patents
A kind of the threedimensional model generation method and system of workpiece Download PDFInfo
- Publication number
- CN109840934A CN109840934A CN201711226524.2A CN201711226524A CN109840934A CN 109840934 A CN109840934 A CN 109840934A CN 201711226524 A CN201711226524 A CN 201711226524A CN 109840934 A CN109840934 A CN 109840934A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- target
- image
- flat image
- submodule
- 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 37
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 32
- 230000009466 transformation Effects 0.000 claims abstract description 32
- 238000009877 rendering Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000003190 augmentative effect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 239000011800 void material Substances 0.000 description 1
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the invention discloses the threedimensional model generation methods and system of a kind of workpiece.The described method includes: obtaining the parameter information and characteristic information of the flat image information of destination virtual object；The target three-dimensional of destination virtual object is constructed according to parameter information, and generates the respective objects flat image that target three-dimensional corresponds to different view classes；All objective plane images for obtaining target three-dimensional, are matched according to characteristic information with all objective plane images；It obtains and is registrated the target three-dimensional of destination virtual object with flat image according to affine transformation matrices with the highest objective plane image of flat image matching degree, the affine transformation matrices of calculating and target three-dimensional.When the program solves different fictitious zero component assemblings, because of threedimensional model position, posture and the size specification of different components, with flat image be not inconsistent and caused by cannot smoothly assemble the problem of, improve assembly efficiency.
Description
Technical field
The present invention relates to augmented reality fields, and in particular to a kind of the threedimensional model generation method and system of workpiece.
Background technique
AR (Augmented Reality, augmented reality) is a kind of by real world information and virtual world information " nothing
The integrated new technology of seam ", be script is difficult to experience in the certain time spatial dimension of real world entity information (depending on
Feel information, sound, taste, tactile etc.) by science and technology such as computers, after analog simulation, true environment and virtual object
Body has been added to the same picture in real time or space exists simultaneously, and virtual Information application to real world is felt by the mankind
Official is perceived, to reach the sensory experience of exceeding reality.Augmented reality not only presents the information of real world, and
And show virtual information simultaneously, two kinds of information are complementary to one another, are superimposed.In the augmented reality of visualization, Yong Huli
With Helmet Mounted Display, real world with computer graphic is multiple is synthesized together, the true world can be seen around it.
AR is a kind of new way that people pass through that computer carries out visualized operation to complex data and interacts, with traditional man-machine boundary
The window-operating of face and prevalence is compared, and AR is haveed a qualitative leap in technical idea.
During actual learning, when being related to components and assembling, especially by the plan view of components to group
The conversion for filling figure, is all often to be given lessons by teaching material and computer to carry out Classroom theory, when tradition is given lessons, figure, figure
It is two dimensional image form that piece etc. is most of, and vividness and verisimilitude are difficult to attract the attention of student, and for being related to
For components and the image of assembly one kind, traditional two dimensional image is more abstract, and inconvenience understands, influences learning efficiency.And
With the utilization of AR, people's also increasingly effect of the concern AR in giving lessons especially converts two dimensional image to lively void
Quasi- 3-D image.Components are assembled, due to the threedimensional model and practical two dimensional image of the virtual components of the difference of building
There are different differences for position and posture and size specification, thus between different virtual components specification may there is also difference,
Assembly efficiency is caused to reduce.
Summary of the invention
The embodiment of the present invention provides the threedimensional model generation method and system of a kind of workpiece, can be efficient by two dimensional image
The virtual three-dimensional model for being converted into virtual three-dimensional model, and constructing can be registrated more particularly to zero with practical two dimensional image
When component and assembly, the position of different virtual components can be made to be consistent with posture and specification with flat image, to realize
Smoothly assembly.
The embodiment of the present invention the following technical schemes are provided:
A kind of threedimensional model generation method of workpiece, comprising the following steps:
The flat image information of destination virtual object is obtained, and obtains the parameter information and characteristic information of the flat image；
The target three-dimensional of the destination virtual object is constructed according to the parameter information of the flat image, and is generated
The target three-dimensional corresponds to the respective objects flat image of different view classes；
All objective plane images for obtaining the target three-dimensional, according to the characteristic information and all targets
Flat image is matched；
It obtains and the highest objective plane image of the flat image matching degree, calculating and the target three-dimensional
Affine transformation matrices, according to the affine transformation matrices by the target three-dimensional of the destination virtual object and described flat
Face image registration simultaneously makes corresponding adjustment；
Target three-dimensional after obtaining registration, and be projected in default screen.
In order to solve the above technical problems, the embodiment of the present invention also the following technical schemes are provided:
A kind of threedimensional model generation system of workpiece, the system comprises:
Image collection module, three-dimensional building module, two-dimentional generation module, characteristic matching module, registration module and projection
Module；
Described image obtains module, for obtaining the parameter of the destination virtual object from the flat image of destination virtual object
Information and characteristic information；
The three-dimensional building module, the target for the destination virtual object according to the flat image information architecture are three-dimensional
Model；
The two dimension generation module corresponds to the respective objects plan view of different view classes for generating the target three-dimensional
Picture；
The characteristic matching module, for according to the characteristic information and all targets of the target three-dimensional
Flat image is matched；
The registration module for acquisition and the highest objective plane image of the flat image matching degree, and is counted
The affine transformation matrices with the target three-dimensional are calculated, it will be described in the destination virtual object according to the affine transformation matrices
Target three-dimensional is registrated to the flat image and makes corresponding adjustment；
The projection module, for the 3-D image after the rendering to be projected in screen.
The threedimensional model generation method and system of a kind of workpiece provided in this embodiment based on augmented reality, pass through acquisition
Parameter information and characteristic information in the flat image of destination virtual object construct the target three-dimensional of destination virtual object, and raw
The respective objects flat image that different view classes are corresponded at the target three-dimensional, according to the characteristic information and the target three
All objective plane images of dimension module are matched, and are obtained flat with the highest target of the flat image matching degree
Face image, with this construct the target three-dimensional to the flat image affine transformation matrices, according to the affine variation
The target three-dimensional is registrated to the flat image and makes corresponding adjustment by matrix, is finally projected to default screen.This
Invention by the virtual three-dimensional model of building and practical two dimensional image autoregistration and can make corresponding adjustment more particularly to zero
When part and assembly, the position of different virtual components can be made to be consistent with posture and specification with flat image, to realize suitable
Benefit assembly.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow diagram of the threedimensional model generation method of workpiece provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of the threedimensional model generation method of another workpiece provided in an embodiment of the present invention；
Fig. 3 is that the threedimensional model of workpiece provided in an embodiment of the present invention generates the structural schematic diagram of system.
Specific embodiment
Schema is please referred to, wherein identical component symbol represents identical component, the principle of the present invention is to implement one
It is illustrated in computing environment appropriate.The following description be based on illustrated by the specific embodiment of the invention, should not be by
It is considered as the limitation present invention other specific embodiments not detailed herein.
Description and claims of this specification and term " first " in above-mentioned attached drawing, " second ", " third " etc.
(if present) is to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be appreciated that this
The object of sample description is interchangeable under appropriate circumstances.In addition, term " includes " and " having " and their any deformation, meaning
Figure, which is to cover, non-exclusive includes.
Term as used herein " module " can regard the software object to execute in the arithmetic system as.It is somebody's turn to do herein not
Same component, module, engine and service can be regarded as the objective for implementation in the arithmetic system.And the device and method being somebody's turn to do herein is excellent
Being implemented in the form of software for choosing, can also be implemented, within that scope of the present invention on hardware certainly.
It will be described in detail respectively below.
Referring to Fig. 1, Fig. 1 is a kind of process signal of threedimensional model generation method of workpiece provided in an embodiment of the present invention
Figure, the embodiment of the present invention method include:
Step S101, obtains the flat image information of destination virtual object, and obtain the parameter information of the flat image with
Characteristic information.
Firstly, first determine destination virtual object, determine the destination virtual object method can there are many, for example can first sentence
Whether the image that breaks is several picture, if so, further judge the image for two-dimensional image or three-dimension space image,
It does not need production threedimensional model then if two-dimensional image, namely does not need to be determined as destination virtual object；If three-dimensional space
Between image the image is then determined as destination virtual object.
Specifically, obtaining the flat image information of current goal virtual object by the camera in augmented reality glasses, sweep
The flat image information is retouched, the parameter information and characteristic information of the flat image are obtained.Wherein, the parameter information includes
The information such as length, width, height and color；The characteristic information includes the information such as angle point and line segment, and the angle point is song
The point that rate changes greatly.
Step S102 constructs the target three-dimensional mould of the destination virtual object according to the parameter information of the flat image
Type, and generate the respective objects flat image that the target three-dimensional corresponds to different view classes.
Specifically, virtual target three-dimensional is constructed according to the parameter information of the destination virtual object, because of institute
The ideal three-dimensional structure that target three-dimensional is the destination virtual object is stated, so it cannot be guaranteed that with described during building
The flat image information of destination virtual object remains exactly the same, it is therefore desirable to divide to the target three-dimensional different
Depending on class, multiple objective plane images are converted depending on class by described by the target three-dimensional, and to the objective plane image
Carry out angle point grid, and the angle point of these objective plane images be it is known, in the target three-dimensional therewith one by one
Corresponding angle point information is also known, i.e., the described target three-dimensional has been calibrated between the objective plane image, can
Calculate ideal three-dimensional model to objective plane image affine transformation matrices.
Wherein, each view class includes the viewpoint with same alike result, and it is three-dimensional that each viewpoint corresponds to the target
One width 2D image of model, attribute is identical to refer to that the set of the angle point in the corresponding 2D image of these viewpoints is identical.
Step S103 obtains all objective plane images of the target three-dimensional, according to the characteristic information and institute
There is the objective plane image to be matched.
Specifically, obtaining all objective plane images and corresponding angle point information of the target three-dimensional, obtain
The characteristic information of the flat image determines that the flat image belongs to which of described target three-dimensional view class,
The similarity degree of this 2 angle points can be determined by comparing the grayscale information of 2 angle point surrounding pixels to determine.Then root again
Corners Matching is carried out according to the characteristic information of the flat image and the objective plane image of the view class.
Step S104 is obtained and the highest objective plane image of the flat image matching degree, calculating and the mesh
The affine transformation matrices for marking threedimensional model, according to the affine transformation matrices by the target three-dimensional mould of the destination virtual object
Type is registrated to the flat image and makes corresponding adjustment.
Specifically, acquisition and the highest objective plane image of the flat image matching degree, calculate out the target
Flat image to flat image transformation matrix, in conjunction with the target three-dimensional to the affine change of the objective plane image
Change matrix, the target three-dimensional can be obtained to the affine transformation matrices of the flat image, it can be to the target three
Dimension module is registrated.
Step S105, the target three-dimensional after obtaining registration, and be projected in default screen.
Specifically, adjustment and amendment, the plan view with destination virtual object has been carried out in the target three-dimensional after registration
The position of picture is consistent with posture and specification, and the target three-dimensional after obtaining registration is simultaneously projected in default screen.
From the foregoing, it will be observed that the threedimensional model generation method of workpiece provided in an embodiment of the present invention, first acquisition destination virtual object
Flat image parameter information and characteristic information, construct the target three-dimensional of destination virtual object, and generate the target three
Dimension module corresponds to the respective objects flat image of different view classes, all according to the characteristic information and the target three-dimensional
The objective plane image is matched, obtain with the highest objective plane image of the flat image matching degree, with this
Construct the target three-dimensional to the flat image affine transformation matrices, according to the affine transformation matrices by the mesh
Mark threedimensional model is registrated with the flat image.
According to the description of a upper embodiment, it will illustrate the threedimensional model of workpiece of the invention with specific embodiment below
Generation method.
Referring to Fig. 2, the present embodiment will be described with the angle of components and assembly based on augmented reality, Fig. 2
For the flow diagram of the threedimensional model generation method of another workpiece provided in an embodiment of the present invention, comprising:
Step S201 scans the flat image of target components and the information that gets parms.
Firstly, first determining whether the flat image is destination virtual object, first judge whether the flat image is geometry
Image, if so, further judging the flat image for two-dimensional image or three-dimension space image, if three-dimensional space
The image is then determined as destination virtual object by image.
Further, the flat image of the target components is scanned, and the information that gets parms, the parameter information include
Length, width and color etc. information.
Step S202, scans the flat image and successively label connected region is denoised；Obtain the flat image
In the angle point information and edge line segment；The pseudo- angle point in the angle point information is removed using Linear Discriminant Method.
Specifically, before carrying out feature extraction to the flat image, first the flat image is denoised, generally
It is realized using connection labeling algorithm.Specifically, flat image described in whole picture is first scanned, successively marks and finds according to sequencing
Connected region (gray value of the region internal point is in identical range) and count its area, if area is less than default threshold
Value, then set the gray value of all the points in this region to the average gray of the point in its neighbouring largest connected region.
Then the extraction of angle point, but the presence because there is pseudo- angle point are carried out, so further removing in the angle point information
Pseudo- angle point, such as target components of polygonal outer shape can obtain the edge line segment in the flat image, be sentenced using straight line
The other method removal pseudo- angle point.
Step S203 constructs the target three-dimensional of the target components according to the parameter information.
Specifically, by obtaining the parameter information of the flat image, such as length, width, height and color
Equal parameter informations, are parsed and are constructed the virtual target three-dimensional of the target components.
Step S204 carries out view class to the target three-dimensional and divides；It is flat to generate the different corresponding targets of the view class
Face image.
Specifically, the target three-dimensional is divided into different view classes, after determining the view class, by the view class
Multiple objective plane images are converted by the target three-dimensional, that is, to determine the corresponding representativeness of each view class
Objective plane image, only those contrasts need to be selected preferable here, the more visible image of angle point, and flat to the target
The angle point of face image carries out manual identified and calibration, and the angle point of these objective plane images is known.
Step S205 obtains the corresponding objective plane image of all view classes of the target three-dimensional；Described in acquisition
Flat image, and matched one by one according to the characteristic information with all objective plane images, obtain matching result.
Wherein, the angle point of the flat image is matched with the angle point of the objective plane image, can be obtained after matching
Then the relational matrix of one normalized cumulant counts the number wherein close to 1, then by the flat image to be matched
Objective plane image corresponding with all view classes all matches once, finally chooses the number of point pair of the normalized cumulant close to 1
That most view classes are as matching result.
Step S206 is obtained and the highest objective plane image of the flat image matching degree, calculating and the mesh
Mark the affine transformation matrices of threedimensional model.
Specifically, acquisition and the highest objective plane image of the flat image matching degree, make according to mahalanobis distance
To further determine, calculate the target three-dimensional to the flat image affine transformation matrices.
Step S207, according to the affine transformation matrices by the target three-dimensional of the target components with it is described
Flat image registration, and the target three-dimensional is adjusted accordingly.
Specifically, the target three-dimensional of the target components is put down with described according to the affine transformation matrices
Face image registration, and the target three-dimensional is adjusted accordingly, the target three-dimensional after registration is put down with described
Face image posture having the same and coordinate.
Step S208 carries out figure rendering to the target three-dimensional, to obtain 3-D image；After the rendering
3-D image is projected in screen.
Specifically, according to the parameter information of the flat image, figure is carried out to the threedimensional model after registration
Rendering, to obtain 3-D image；The threedimensional model image after rendering is projected in screen again.Wherein, the rendering has
Various software, such as: each CG software carries rendering engine, and there are also RenderMan etc..Image rendering may include light efficiency effect
Processing, texture padding, Difference Clouds etc..
Wherein, multiple target components can be registrated to form virtual three-dimensional model one by one, can also be simultaneously to multiple targets zero
Part is registrated, and virtual three-dimensional model is formed simultaneously；It can be based on augmented reality to the virtual three-dimensional model of multiple components
It is assembled.Or virtual three-dimensional model building directly can be carried out to practical set figure, the appearance of different virtual components can be made
State and position are consistent with practical set figure, to realize smoothly assembly.Wherein each fictitious zero in virtual three-dimensional installation diagram
Component can be extracted individually, can carry out 360 degree of browsings.
From the foregoing, it will be observed that the threedimensional model generation method of image provided in an embodiment of the present invention, first acquisition target components
Flat image parameter information and characteristic information, construct the target three-dimensional of target components, and generate the target three
Dimension module corresponds to the respective objects flat image of different view classes, all according to the characteristic information and the target three-dimensional
The objective plane image is matched, obtain with the highest objective plane image of the flat image matching degree, with this
Construct the target three-dimensional to the flat image affine transformation matrices, according to the affine transformation matrices by the mesh
Mark threedimensional model and the flat image autoregistration.To make the different virtually positions of components and posture and specification and put down
Face image is consistent, and then realizes smoothly assembly.
For the ease of the threedimensional model generation method of better implementation image provided in an embodiment of the present invention, the present invention is implemented
Example additionally provides a kind of system of threedimensional model generation method based on above-mentioned image, and the present embodiment will be based on augmented reality
Components and the angle of assembly are described.
As shown in figure 3, Fig. 3 is that the threedimensional model of workpiece provided in an embodiment of the present invention generates the structural schematic diagram of system,
The threedimensional model of the workpiece generate system include: image collection module 301, three-dimensional building module 302, two-dimentional generation module 303,
Characteristic matching module 304, registration module 305 and projection module 306.
Described image obtains module 301, for obtaining the target components from the flat image of target components
Parameter information and characteristic information, wherein the characteristic information includes angle point information.
Further, described image obtains module 301 and specifically includes: image acquisition submodule, parameter acquisition submodule, spy
Sign acquisition submodule and feature remove pseudo- submodule；Described image acquisition submodule, for scanning and obtaining the target zero
The flat image of part.The parameter acquisition submodule, for obtaining the parameter information in the flat image, the parameter information
Including length, width and color；To construct the target three-dimensional of the target components.
The feature acquisition submodule, for obtaining the characteristic information in the flat image, such as angle point information；It is described
Pseudo- submodule is removed, for removing the pseudo- angle point in the angle point information.
Specifically, before carrying out feature extraction to the flat image, first the flat image is denoised, generally
It is realized using connection labeling algorithm.Then the feature acquisition submodule carries out the extraction of angle point, but because there is depositing for pseudo- angle point
, so the pseudo- angle point for going pseudo- submodule further to remove in the angle point information, such as the target of polygonal outer shape
Components can obtain the edge line segment in the flat image, using the Linear Discriminant Method removal pseudo- angle point.
The three-dimensional building module 302, the target for the target components according to the flat image information architecture
Threedimensional model；
Further, the three-dimensional building module 302 specifically includes: Parameter analysis of electrochemical submodule and building submodule；Institute
Parameter analysis of electrochemical submodule is stated, for parsing the parameter information；The building submodule, for constructing the target according to parameter
Threedimensional model.
Specifically, by obtaining the parameter information of the flat image, such as length, width, height and color
Equal parameter informations, are parsed and are constructed the virtual target three-dimensional of the target components.
The two dimension generation module 303, the respective objects that different view classes are corresponded to for generating the target three-dimensional are put down
Face image；Wherein, the two-dimentional generation module 303 specifically includes: view class divides submodule, two dimension generates submodule and angle point
Extracting sub-module；
The view class divides submodule, for the target three-dimensional to be divided into different view classes；The two dimension generates
Submodule converts multiple objective plane images for the target three-dimensional depending on class by described, it is corresponding to generate different view classes
Objective plane image；Angle point grid submodule, for obtaining the angle point information of the objective plane image.
Specifically, the target three-dimensional is divided into different view classes, after determining the view class, by the view class
Multiple objective plane images are converted by the target three-dimensional, that is, to determine the corresponding representativeness of each view class
Objective plane image, only those contrasts need to be selected preferable here, the more visible image of angle point, and flat to the target
The angle point of face image carries out manual identified and calibration, and the angle point of these objective plane images is known.
The characteristic matching module 304, for according to the characteristic information and the target three-dimensional it is all described in
Objective plane image is matched.
Specifically, the angle point of the flat image is matched with the angle point of the objective plane image, meeting after matching
The relational matrix of a normalized cumulant is obtained, the number wherein close to 1 is then counted, then by the plane to be matched
Image and the corresponding objective plane image of all view classes all match once, finally choose point pair of the normalized cumulant close to 1
That most view class of number is as matching result.
The registration module 305, for acquisition and the highest objective plane image of the flat image matching degree, and
Calculate with the affine transformation matrices of the target three-dimensional, according to the affine transformation matrices by the institute of the target components
Target three-dimensional is stated to be registrated to the flat image and make corresponding adjustment to the target three-dimensional.
The registration module 305 includes: data processing submodule, registration submodule, rendering submodule；The data processing
Submodule, the affine transformation matrices for calculating the target three-dimensional to the flat image；The registration submodule is used
In the target three-dimensional is registrated with the flat image and is adjusted accordingly to the target three-dimensional；Institute
Rendering submodule is stated, for carrying out figure rendering to the threedimensional model after registration, to obtain 3-D image.
Specifically, the target three-dimensional of the target components is put down with described according to the affine transformation matrices
Face image registration, and the target three-dimensional is adjusted accordingly, the target three-dimensional after registration is put down with described
Face image posture having the same and coordinate.
The projection module 306, for the 3-D image after the rendering to be projected in screen.
Specifically, according to the parameter information of the flat image, figure is carried out to the threedimensional model after registration
Rendering, to obtain 3-D image；The threedimensional model image after rendering is projected in screen again.
From the foregoing, it will be observed that the threedimensional model of workpiece provided in an embodiment of the present invention generates system, target components are obtained first
Flat image parameter information and characteristic information, construct the target three-dimensional of target components, and generate the target three
Dimension module corresponds to the respective objects flat image of different view classes, all according to the characteristic information and the target three-dimensional
The objective plane image is matched, obtain with the highest objective plane image of the flat image matching degree, with this
Construct the target three-dimensional to the flat image affine transformation matrices, according to the affine transformation matrices by the mesh
Mark threedimensional model and the flat image autoregistration.To make the different virtually positions of components and posture and specification and put down
Face image is consistent, and then realizes smoothly assembly.
It should be noted that those of ordinary skill in the art will appreciate that whole in the various methods of above-described embodiment or
Part steps are relevant hardware can be instructed to complete by program, which can store in computer-readable storage medium
It in matter, is such as stored in the memory of terminal, and is executed by least one processor in the terminal, can be wrapped in the process of implementation
Include the process of the embodiment such as information issuing method.Wherein, storage medium may include: read-only memory (ROM, Read Only
Memory), random access memory (RAM, Random Access Memory), disk or CD etc..
A kind of image processing method provided in an embodiment of the present invention and system are described in detail above, each function
Module can integrate in a processing chip, is also possible to modules and physically exists alone, can also two or two with
Upper module is integrated in a module.Above-mentioned integrated module both can take the form of hardware realization, can also use software
The form of functional module is realized.It is used herein that a specific example illustrates the principle and implementation of the invention, with
The explanation of upper embodiment is merely used to help understand method and its core concept of the invention；Meanwhile for the technology of this field
Personnel, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion this theory
Bright book content should not be construed as limiting the invention.
Claims (10)
1. a kind of threedimensional model generation method of workpiece, which comprises the following steps:
The flat image information of destination virtual object is obtained, and obtains the parameter information and characteristic information of the flat image；
The target three-dimensional of the destination virtual object is constructed according to the parameter information of the flat image, and described in generation
Target three-dimensional corresponds to the respective objects flat image of different view classes；
All objective plane images for obtaining the target three-dimensional, according to the characteristic information and all objective planes
Image is matched；
It obtains and is imitated with the highest objective plane image of the flat image matching degree, calculating with the target three-dimensional
Transformation matrices are penetrated, according to the affine transformation matrices by the target three-dimensional of the destination virtual object and the plan view
As being registrated and making corresponding adjustment；
Target three-dimensional after obtaining registration, and be projected in default screen.
2. the method as described in claim 1, which is characterized in that the flat image information for obtaining destination virtual object, and obtain
The parameter information of the flat image is taken to specifically include with characteristic information:
The flat image is scanned and the information that gets parms, for constructing the target three-dimensional of the destination virtual object；
It scans the flat image and successively marks connected region, the flat image is denoised using connection labeling algorithm；
Obtain the angle point information in the flat image；
The edge line segment in the flat image is obtained, the pseudo- angle point in the angle point information is removed using Linear Discriminant Method.
3. the method as described in claim 1, which is characterized in that described to be constructed according to the parameter information of the flat image
The target three-dimensional of the destination virtual object, and generate the respective objects plane that the target three-dimensional corresponds to different view classes
The step of image, specifically includes:
The target three-dimensional of the destination virtual object is constructed according to the parameter information；
View class is carried out to the target three-dimensional to divide；
Generate the different corresponding objective plane images of view class.
4. the method as described in claim 1, which is characterized in that described according to the characteristic information and the target three-dimensional
All objective plane images corresponding depending on class carry out matching
Obtain the corresponding objective plane image of all view classes of the target three-dimensional；
The flat image is obtained, and is matched one by one according to the characteristic information with all objective plane images；
The corresponding objective plane image of the highest view class of matching degree is obtained, as matching result.
5. the method as described in claim 1, which is characterized in that described according to the affine transformation matrices that the target is empty
After the target three-dimensional of quasi- object is registrated with the flat image, the method also includes:
Figure rendering is carried out to the target three-dimensional, to obtain 3-D image；
3-D image after the rendering is projected in default screen.
6. a kind of threedimensional model of workpiece generates system characterized by comprising image collection module, three-dimensional building module, two
Tie up generation module, characteristic matching module, registration module and projection module；
Described image obtains module, for obtaining the parameter information of the destination virtual object from the flat image of destination virtual object
With characteristic information；
The three-dimensional building module, the target three-dimensional mould for the destination virtual object according to the flat image information architecture
Type；
The two dimension generation module corresponds to the respective objects flat image of different view classes for generating the target three-dimensional；
The characteristic matching module, for according to the characteristic information and all objective planes of the target three-dimensional
Image is matched；
The registration module, for obtain with the highest objective plane image of the flat image matching degree, and calculate with
The affine transformation matrices of the target three-dimensional, according to the affine transformation matrices by the target of the destination virtual object
Threedimensional model is registrated to the flat image and makes corresponding adjustment；
The projection module, for the 3-D image after the rendering to be projected in screen.
7. system as claimed in claim 6, which is characterized in that described image obtains module and specifically includes: image obtains submodule
Block, parameter acquisition submodule, feature acquisition submodule and remove pseudo- submodule；
Described image acquisition submodule, for obtaining the flat image of the destination virtual object；
The parameter acquisition submodule, for obtaining the parameter information in the flat image, the parameter information include length,
Width and color；
The feature acquisition submodule, for obtaining the angle point information in the flat image；
It is described to remove pseudo- submodule, for removing the pseudo- angle point in the angle point information.
8. system as claimed in claim 6, which is characterized in that the three-dimensional building module specifically includes: Parameter analysis of electrochemical submodule
Block and building submodule；
The Parameter analysis of electrochemical submodule, for parsing the parameter information；
The building submodule, for constructing the target three-dimensional according to parameter.
9. system as claimed in claim 6, which is characterized in that the two dimension generation module specifically includes: view class divides submodule
Block, two dimension generate submodule and angle point grid submodule；
The view class divides submodule, for the target three-dimensional to be divided into different view classes；
The two dimension generates submodule, for generating the corresponding objective plane image of different view classes；
Angle point grid submodule, for obtaining the angle point information of the objective plane image.
10. system as claimed in claim 6, which is characterized in that the registration module includes: data processing submodule, registration
Submodule, rendering submodule；
The data processing submodule, the affine transformation matrices for calculating the target three-dimensional to the flat image；
The registration submodule, for being registrated the target three-dimensional to the flat image and making corresponding tune
It is whole；
The rendering submodule, for carrying out figure rendering to the threedimensional model after registration, to obtain 3-D image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711226524.2A CN109840934A (en) | 2017-11-29 | 2017-11-29 | A kind of the threedimensional model generation method and system of workpiece |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711226524.2A CN109840934A (en) | 2017-11-29 | 2017-11-29 | A kind of the threedimensional model generation method and system of workpiece |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109840934A true CN109840934A (en) | 2019-06-04 |
Family
ID=66882030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711226524.2A Pending CN109840934A (en) | 2017-11-29 | 2017-11-29 | A kind of the threedimensional model generation method and system of workpiece |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109840934A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222465A (en) * | 2019-06-19 | 2019-09-10 | 南通云创工业设计有限公司 | A kind of design method and device of product |
| CN110390258A (en) * | 2019-06-05 | 2019-10-29 | 东南大学 | Image object three-dimensional information mask method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778741A (en) * | 2014-01-14 | 2015-07-15 | 北大方正集团有限公司 | Method and device for converting two-dimensional figure into three-dimensional figure |
| JP2016126425A (en) * | 2014-12-26 | 2016-07-11 | Kddi株式会社 | Free viewpoint image generation device, method and program |
| CN106249881A (en) * | 2016-07-21 | 2016-12-21 | 江苏奥格视特信息科技有限公司 | Augmented reality view field space and virtual three-dimensional target dynamic method for registering |
| CN107393000A (en) * | 2017-08-24 | 2017-11-24 | 广东欧珀移动通信有限公司 | Image processing method, device, server and computer-readable recording medium |
-
2017
- 2017-11-29 CN CN201711226524.2A patent/CN109840934A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778741A (en) * | 2014-01-14 | 2015-07-15 | 北大方正集团有限公司 | Method and device for converting two-dimensional figure into three-dimensional figure |
| JP2016126425A (en) * | 2014-12-26 | 2016-07-11 | Kddi株式会社 | Free viewpoint image generation device, method and program |
| CN106249881A (en) * | 2016-07-21 | 2016-12-21 | 江苏奥格视特信息科技有限公司 | Augmented reality view field space and virtual three-dimensional target dynamic method for registering |
| CN107393000A (en) * | 2017-08-24 | 2017-11-24 | 广东欧珀移动通信有限公司 | Image processing method, device, server and computer-readable recording medium |
Non-Patent Citations (1)
| Title |
|---|
| 范志超等: "增强现实数控加工中虚拟注册技术研究", 《机械与电子》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110390258A (en) * | 2019-06-05 | 2019-10-29 | 东南大学 | Image object three-dimensional information mask method |
| CN110222465A (en) * | 2019-06-19 | 2019-09-10 | 南通云创工业设计有限公司 | A kind of design method and device of product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107273502B (en) | Image geographic labeling method based on spatial cognitive learning | |
| CN104463948B (en) | Seamless visualization method for three-dimensional virtual reality system and geographic information system | |
| CN103729885B (en) | Various visual angles projection registers united Freehandhand-drawing scene three-dimensional modeling method with three-dimensional | |
| CN107330903B (en) | Skeleton extraction method of human point cloud model | |
| CN108305312A (en) | The generation method and device of 3D virtual images | |
| Yang et al. | A multi-task Faster R-CNN method for 3D vehicle detection based on a single image | |
| CN107798725B (en) | Android-based two-dimensional house type identification and three-dimensional presentation method | |
| CN111932673B (en) | Object space data augmentation method and system based on three-dimensional reconstruction | |
| WO2023284713A1 (en) | Three-dimensional dynamic tracking method and apparatus, electronic device and storage medium | |
| CN109308734B (en) | 3D character generation method and device, equipment and storage medium thereof | |
| Busking et al. | Dynamic Multi‐View Exploration of Shape Spaces | |
| CN106204746B (en) | A kind of augmented reality system of achievable 3D models live paint | |
| CN104537705A (en) | Augmented reality based mobile platform three-dimensional biomolecule display system and method | |
| CN109840934A (en) | A kind of the threedimensional model generation method and system of workpiece | |
| Doungmala et al. | Investigation into the Application of Image Modeling Technology in the Field of Computer Graphics | |
| CN116385619B (en) | Object model rendering method, device, computer equipment and storage medium | |
| Xiaokang et al. | Research on augmented reality method based on improved ORB algorithm | |
| CN104091318B (en) | A kind of synthetic method of Chinese Sign Language video transition frame | |
| Levene | A framework for non-realistic projections | |
| CN114972601A (en) | Model generation method, face rendering device and electronic equipment | |
| Jianu et al. | A coloring solution to the edge crossing problem | |
| CN102938156B (en) | Planar note configuration method based on integral images | |
| Sela et al. | Generation of view dependent models using free form deformation | |
| Zhao | Video/Image Processing on FPGA. | |
| CN117132501B (en) | Human body point cloud cavity repairing method and system based on depth camera |
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: 20190604 |