CN109089105A - Model generating means and method based on depth perception coding - Google Patents
Model generating means and method based on depth perception coding Download PDFInfo
- Publication number
- CN109089105A CN109089105A CN201811008355.XA CN201811008355A CN109089105A CN 109089105 A CN109089105 A CN 109089105A CN 201811008355 A CN201811008355 A CN 201811008355A CN 109089105 A CN109089105 A CN 109089105A
- Authority
- CN
- China
- Prior art keywords
- initial image
- module
- target
- coding
- depth
- 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 discloses a kind of model generating means and method based on depth perception coding, model generating means include a 3D video camera and a processing end, processing end includes an acquisition module, a processing module and a generation module, processing end further includes a database, the database includes several depth perception codings, and the 3D video camera is used to obtain the initial image of a secondary photographic subjects;Module is obtained for obtaining the target depth perceptual coding with initial Image Matching in the database;Processing module is used to adjust the parameter of the target depth perceptual coding according to initial image;Generation module is used to generate the 3D model of the photographic subjects according to the target depth perceptual coding for adjusting parameter.The present invention can digitize 3D image, by a secondary 3D video generation one closing, complete 3D model, and so that the 3D image obtained is more easier management, control, and can reduce operation consumed resource, reduce 3D image and taken up space.
Description
Technical field
The present invention relates to a kind of model generating means and method based on depth perception coding.
Background technique
3D video camera, what is utilized is the video camera of 3D camera lens manufacture, usually there are two tools more than pick-up lens, spacing and people
Eye spacing is close, can shoot the similar seen different images for being directed to Same Scene of human eye.Holographic 3D has 5 camera lens of disk
More than, by dot grating image Huo Ling shape raster holographic imaging can the comprehensive same image of viewing, can such as come to its border personally.
The 3D revolution so far of First 3D video camera is unfolded all around Hollywood weight pound sheet and important competitive sports.With
The appearance of 3D video camera, this technology distance domestic consumer close step again.After the release of this video camera, we are from now on
Each unforgettable moment of life, such as the first step that child steps, celebration of graduating from university etc. can be captured with 3D camera lens.
Usually there are two the above camera lenses for 3D video camera.The function of 3D video camera itself, can be by two just as human brain
Lens image is fused together, and becomes a 3D rendering.These images can play on 3D TV, and spectators wear so-called master
Dynamic formula shutter glasses may be viewed by, and can also pass through naked eye 3D display equipment direct viewing.3D shutter glasses can be with per second 60
Secondary speed enables the eyeglass fast crosstalk of left and right glasses switch.This means that each eye is it is seen that Same Scene is slightly shown not
Same picture, so brain can be thus to be the single photo presented in appreciation with 3D for it.
The image that existing 3D video camera obtains does not allow easy to handle, control, and single 3D video camera is inconvenient to model.
Summary of the invention
The technical problem to be solved by the present invention is to be not easy to locate for the image for overcoming 3D video camera in the prior art to obtain
Reason, control, it has not been convenient to the defect of modeling, 3D image can be digitized by providing one kind, closed by a secondary 3D video generation one,
Complete 3D model, and so that the 3D image obtained is more easier management, control, and can reduce operation consumed resource, reduce
The model generating means and method based on depth perception coding that 3D image is taken up space.
The present invention is to solve above-mentioned technical problem by following technical proposals:
A kind of model generating means based on depth perception coding, it is characterized in that, the model generating means include one
A 3D video camera and a processing end, the processing end obtains module, a processing module and a generation module including one, described
Processing end further includes a database, and the database includes several depth perception codings,
The 3D video camera is used to obtain the initial image of a secondary photographic subjects;
The module that obtains is compiled for obtaining to perceive with the target depth of the initial Image Matching in the database
Code;
The processing module is used to adjust the parameter of the target depth perceptual coding according to the initial image;
The generation module is used to generate the 3D of the photographic subjects according to the target depth perceptual coding for adjusting parameter
Model.
The digital spot cloud that the depth perception, which is encoded to, can edit, optimizes and simplify, and perceptual coding can be
The digital spot cloud pre-set, each of perceptual coding digital point can have between the label and digital point of oneself
There are certain conduct the relation.
The parameter can be the parameter for adjustable shape, since depth perception coding can adjust the shape in space,
The spatial form that depth perception encodes is adjusted to the depth perception that shape identical with initial image has just obtained initial image
Coding.
Preferably, the processing end further includes an identification module,
Identification module position of the initial image in 3D model for identification;
The processing module is used to adjust the target depth perceptual coding and the position pair according to the initial image
Answer the parameter in region.
Preferably, each depth perception coding in the database includes several viewing areas, each viewing area is equal
Depth perception, which is observed, by a virtual view points in space encodes obtained region,
The identification module corresponding target observations region of the initial image for identification;
It is described obtain the target observations region that module is used to encode by searching for each depth perception obtain with it is described initially
The immediate target depth perceptual coding of image shape;
The processing module is used to adjust the target observations area of the target depth perceptual coding according to the initial image
The parameter in domain.
Preferably, the processing end further includes a placement module,
The placement module is used to initial image overlap place depth perception coding to obtain image on initial image
Distance of the point to depth perception coding;
One depth perception is encoded, the distance phase for obtaining module and being used to encode depth perception each imaging point
Whole matching value is obtained, the smallest depth perception of whole matching value numerical value is encoded to the target depth perception and compiles
Code.
Preferably, the depth perception coding includes pixel layer and structure sheaf, the depth perception coding is equipped with several
For the control point of control structure layer shape, the processing module be used for according to the initial image shape adjustment control point with
Adjust the parameter of the target depth perceptual coding.
Preferably, the processing end includes a placement module,
The placement module is used to place target depth perceptual coding and initial image overlap to obtain target depth sense
Know the vertical range for encoding upper control point to initial image;
The processing module be also used to obtain it is described apart from maximum control point be target control point, and by the target control
Point is made to the mobile distance of initial image direction;
The processing module is also used to the surrounding control point around target control point is mobile to initial image direction
Distance is adjusted, the adjustment at each surrounding control point is inversely proportional at a distance from surrounding control point to target control point apart from size, institute
It states adjustment distance and is less than target control point moving distance.
The present invention also provides a kind of model generating methods based on digitized image, it is characterized in that, the model generates
Method realizes that the model generating means include a 3D video camera and a processing end, described by a model generating means
Processing end includes that an acquisition module, a processing module and a generation module, the processing end further include a database, the number
It include several depth perception codings according to library, the model generating method includes:
The 3D video camera obtains the initial image of a secondary photographic subjects;
The acquisition module obtains and the target depth perceptual coding of the initial Image Matching in the database;
The processing module adjusts the parameter of the target depth perceptual coding according to the initial image;
The generation module generates the 3D model of the photographic subjects according to the target depth perceptual coding for adjusting parameter.
Preferably, the processing end further includes an identification module, the model generating method includes:
The identification module identifies position of the initial image in 3D model;
The processing module adjusts the target depth perceptual coding area corresponding with the position according to the initial image
The parameter in domain.
Preferably, each depth perception coding in the database includes several viewing areas, each viewing area is equal
Depth perception is observed by a virtual view points in space and encodes obtained region, and the model generating method includes:
The identification module identifies the corresponding target observations region of the initial image;
The module that obtains obtains and the initial image by searching for the target observations region that each depth perception encodes
The immediate target depth perceptual coding of shape;
The processing module adjusts the target observations region of the target depth perceptual coding according to the initial image
Parameter.
Preferably, the processing end further includes a placement module, the model generating method includes:
Depth perception is encoded to place with initial image overlap and be arrived with obtaining imaging point on initial image by the placement module
The distance of depth perception coding;
One depth perception is encoded, it is described obtain module by the distance that depth perception encodes each imaging point be added with
Whole matching value is obtained, the smallest depth perception of whole matching value numerical value is encoded to the target depth perceptual coding.?
On the basis of meeting common sense in the field, above-mentioned each optimum condition, can any combination to get the preferred embodiments of the invention.
The positive effect of the present invention is that:
The present invention can digitize 3D image, by a secondary 3D video generation one closing, complete 3D model, and make to obtain
The 3D image taken is more easier management, control, and can reduce operation consumed resource, reduces 3D image and is taken up space.
Detailed description of the invention
Fig. 1 is the flow chart of the model generating method of the embodiment of the present invention 1.
Specific embodiment
The present invention is further illustrated below by the mode of embodiment, but does not therefore limit the present invention to the reality
It applies among a range.
Embodiment 1
The present embodiment provides a kind of model generating means based on depth perception coding, the model generating means include one
A 3D video camera and a processing end.
The processing end includes an acquisition module, a processing module, a generation module and an identification module, the processing
End can be computer terminal, mobile phone terminal or cloud server.
The processing end further includes a database, and the database includes several depth perception codings.Depth perception coding
It is the data of specification, with pixel (imaging point) for unit, the pixel can be edited image, change parameter.
Depth perception coding is made of vector units, the depth perception coding by vector units building lines and
The intersection point of lines.
Polar plot is according to geometrical property come graphing, and vector can be a point or a line, polar plot and can only lean on
Software Create, it is smaller that file occupies internal space, can be certainly because such image file includes independent separate picture
It is reconfigured by unconfined.Its feature be amplification after image will not be distorted it is unrelated with resolution ratio, be suitable for graphic designs,
Text design and some Mark Designings, Layout Design etc..
The 3D video camera is used to obtain the initial image of a secondary photographic subjects;
The module that obtains is compiled for obtaining to perceive with the target depth of the initial Image Matching in the database
Code;
The processing module is used to adjust the parameter of the target depth perceptual coding according to the initial image;
The generation module is used to generate the 3D of the photographic subjects according to the target depth perceptual coding for adjusting parameter
Model.
The present embodiment can be by one closed spatial model of a secondary 3D video generation, so as to accelerate the life of model
At speed.
Identification module position of the initial image in 3D model for identification;
The processing module is used to adjust the target depth perceptual coding and the position pair according to the initial image
Answer the parameter in region.
In order to rapidly search the matched target depth perceptual coding, the present embodiment passes through the identification to initial image
Can obtain includes which face, position etc. in shooting angle and initial image.For example, initial image is shot by front
It obtains, including eyes, nose and mouth, then the acquisition module is used in the database by searching for 3D model
Front image, that is, no longer need to calculate behind head and search matched target digitization image.
The matched depth perception is encoded to be encoded with the initial immediate depth perception of image space shape.
Further, each depth perception coding in the database includes several viewing areas, each viewing area
Depth perception, which is observed, by a virtual view points in space encodes obtained region.
Depth perception coded markings can be gone out to several regions that can be overlapped by viewing area, pass through initial image
Comparison with viewing area can obtain the target observations region faster, and the initial image can obtain shooting angle,
The shooting angle is the region under the point of observation.
The identification module corresponding target observations region of the initial image for identification;
It is described obtain the target observations region that module is used to encode by searching for each depth perception obtain with it is described initially
The immediate target depth perceptual coding of image shape;
The processing module is used to adjust the target observations area of the target depth perceptual coding according to the initial image
The parameter in domain.
In order to obtain the immediate depth perception coding of shape, the processing end further includes a placement module.
The placement module is used to initial image overlap place depth perception coding to obtain image on initial image
Distance of the point to depth perception coding.
In the present invention, control point on digitized image, imaging point to initial image distance refer between corresponding points away from
From such as the distance of nose to nose, the distance etc. of the corners of the mouth to the corners of the mouth.
One depth perception is encoded, the distance phase for obtaining module and being used to encode depth perception each imaging point
Whole matching value is obtained, the smallest depth perception of whole matching value numerical value is encoded to the target depth perception and compiles
Code.
Referring to Fig. 1, using above-mentioned model generating means, the present embodiment also provides a kind of model generating method, comprising:
Step 100, the 3D video camera obtain the initial image of a secondary photographic subjects;
Step 101, the identification module identify position of the initial image in 3D model;.
In a step 101, the identification module identifies that the corresponding target observations region of the initial image is described to mark
Initial position of the image in 3D model.
Step 102, the acquisition module obtain and the target depth sense of the initial Image Matching in the database
Know coding.
In a step 102, the specific steps that target depth perceptual coding obtains are as follows:
Depth perception is encoded to place with initial image overlap and be arrived with obtaining imaging point on initial image by the placement module
The distance of depth perception coding;
One depth perception is encoded, it is described obtain module by the distance that depth perception encodes each imaging point be added with
Whole matching value is obtained, the smallest depth perception of whole matching value numerical value is encoded to the target depth perceptual coding.
Specifically, at the beginning of the acquisition module obtains by searching for the target observations region that each depth perception encodes and is described
The immediate target depth perceptual coding of beginning image shape searches the smallest depth perception coding of matching value in viewing area.
Step 103, the processing module adjust the target depth perceptual coding and institute's rheme according to the initial image
Set the parameter of corresponding region.
Step 104, the generation module generate the photographic subjects according to the target depth perceptual coding for adjusting parameter
3D model.
Embodiment 2
The present embodiment is substantially the same manner as Example 1, the difference is that only:
The present embodiment provides a kind of specific parameter regulation modes.
The depth perception coding includes pixel layer and structure sheaf, and the depth perception coding is equipped with several for controlling
The control point of structure sheaf shape, the processing module adjust described for the shape adjustment control point according to the initial image
The parameter of target depth perceptual coding.
Specifically, the placement module is used to place target depth perceptual coding and initial image overlap to obtain target
Depth perception encodes upper control point to the vertical range of initial image;
The processing module be also used to obtain it is described apart from maximum control point be target control point, and by the target control
Point is made to the mobile distance of initial image direction;
The processing module is also used to the surrounding control point around target control point is mobile to initial image direction
Distance is adjusted, the adjustment at each surrounding control point is inversely proportional at a distance from surrounding control point to target control point apart from size, institute
It states adjustment distance and is less than target control point moving distance.
The control point is corresponding with pixel (imaging point) point, and the pixel of such as depth perception coding is 5000, wherein
Key point is 1000, this thousand key points and control point correspond.The movement at control control point can control pixel
The movement of point in space is more nearly the depth perception coding closest to initial image with initial image.
Above scheme circulation executes until the distance of whole control point to initial images terminates stream after being respectively less than pre-determined distance
Journey.
Although specific embodiments of the present invention have been described above, it will be appreciated by those of skill in the art that these
It is merely illustrative of, protection scope of the present invention is defined by the appended claims.Those skilled in the art is not carrying on the back
Under the premise of from the principle and substance of the present invention, many changes and modifications may be made, but these are changed
Protection scope of the present invention is each fallen with modification.
Claims (10)
1. a kind of model generating means based on depth perception coding, which is characterized in that the model generating means include one
3D video camera and a processing end, the processing end include an acquisition module, a processing module and a generation module, the place
Reason end further includes a database, and the database includes several depth perception codings,
The 3D video camera is used to obtain the initial image of a secondary photographic subjects;
The target depth perceptual coding that module is obtained for being obtained in the database with the initial Image Matching;
The processing module is used to adjust the parameter of the target depth perceptual coding according to the initial image;
The generation module is used to generate the 3D model of the photographic subjects according to the target depth perceptual coding for adjusting parameter.
2. model generating means as described in claim 1, which is characterized in that the processing end further includes an identification module,
Identification module position of the initial image in 3D model for identification;
The processing module is used to adjust the target depth perceptual coding area corresponding with the position according to the initial image
The parameter in domain.
3. model generating means as claimed in claim 2, which is characterized in that each depth perception coding in the database
Including several viewing areas, it is obtained that each viewing area passes through virtual view points observation depth perception coding in space
Region,
The identification module corresponding target observations region of the initial image for identification;
It is described to obtain the acquisition of target observations region and the initial image that module is used to encode by searching for each depth perception
The immediate target depth perceptual coding of shape;
The processing module is used to adjust the target observations region of the target depth perceptual coding according to the initial image
Parameter.
4. model generating means as described in claim 1, which is characterized in that the processing end further includes a placement module,
The placement module is used to place depth perception coding with initial image overlap and be arrived with obtaining imaging point on initial image
The distance of depth perception coding;
One depth perception is encoded, it is described obtain module be used to encode depth perception each imaging point distance be added with
Whole matching value is obtained, the smallest depth perception of whole matching value numerical value is encoded to the target depth perceptual coding.
5. model generating means as described in claim 1, which is characterized in that the depth perception coding includes pixel layer and knot
Structure layer, the depth perception coding are equipped with several control points for control structure layer shape, and the processing module is for pressing
The parameter of the target depth perceptual coding is adjusted according to the shape adjustment control point of the initial image.
6. model generating means as claimed in claim 5, which is characterized in that the processing end includes a placement module,
The placement module is used to place target depth perceptual coding and initial image overlap to obtain target depth perception and compile
Vertical range of the control point to initial image on code;
The processing module be also used to obtain it is described apart from maximum control point be target control point, and by the target control point
To the mobile distance of initial image direction;
The processing module is also used to adjust the surrounding control point around target control point to initial image direction is mobile
The adjustment of distance, each surrounding control point is inversely proportional at a distance from surrounding control point to target control point apart from size, the tune
Whole distance is less than target control point moving distance.
7. a kind of model generating method based on digitized image, which is characterized in that the model generating method passes through a model
Generating means realize that the model generating means include a 3D video camera and a processing end, and the processing end is obtained including one
Modulus block, a processing module and a generation module, the processing end further include a database, and the database includes several depths
Perceptual coding is spent, the model generating method includes:
The 3D video camera obtains the initial image of a secondary photographic subjects;
The acquisition module obtains and the target depth perceptual coding of the initial Image Matching in the database;
The processing module adjusts the parameter of the target depth perceptual coding according to the initial image;
The generation module generates the 3D model of the photographic subjects according to the target depth perceptual coding for adjusting parameter.
8. model generating method as claimed in claim 7, which is characterized in that the processing end further includes an identification module, institute
Stating model generating method includes:
The identification module identifies position of the initial image in 3D model;
The processing module adjusts the target depth perceptual coding and the position corresponding region according to the initial image
Parameter.
9. model generating method as claimed in claim 8, which is characterized in that each depth perception coding in the database
Including several viewing areas, it is obtained that each viewing area passes through virtual view points observation depth perception coding in space
Region, the model generating method include:
The identification module identifies the corresponding target observations region of the initial image;
The module that obtains obtains and the initial image shape by searching for the target observations region that each depth perception encodes
Immediate target depth perceptual coding;
The processing module adjusts the parameter in the target observations region of the target depth perceptual coding according to the initial image.
10. model generating method as claimed in claim 7, which is characterized in that the processing end further includes a placement module, institute
Stating model generating method includes:
The placement module places depth perception coding with initial image overlap to obtain on initial image imaging point to depth
The distance of perceptual coding;
One depth perception is encoded, the distance that depth perception encodes each imaging point is added to obtain by the module that obtains
Whole matching value, the smallest depth perception of whole matching value numerical value are encoded to the target depth perceptual coding.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811008355.XA CN109089105B (en) | 2018-08-31 | 2018-08-31 | Model generation device and method based on depth perception coding |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811008355.XA CN109089105B (en) | 2018-08-31 | 2018-08-31 | Model generation device and method based on depth perception coding |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109089105A true CN109089105A (en) | 2018-12-25 |
CN109089105B CN109089105B (en) | 2020-06-23 |
Family
ID=64840426
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811008355.XA Active CN109089105B (en) | 2018-08-31 | 2018-08-31 | Model generation device and method based on depth perception coding |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109089105B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160086304A1 (en) * | 2014-09-22 | 2016-03-24 | Ming Chuan University | Method for estimating a 3d vector angle from a 2d face image, method for creating face replacement database, and method for replacing face image |
CN107123160A (en) * | 2017-05-02 | 2017-09-01 | 成都通甲优博科技有限责任公司 | Simulation lift face system, method and mobile terminal based on three-dimensional image |
US20180157901A1 (en) * | 2016-12-07 | 2018-06-07 | Keyterra LLC | Method and system for incorporating contextual and emotional visualization into electronic communications |
CN108305312A (en) * | 2017-01-23 | 2018-07-20 | 腾讯科技(深圳)有限公司 | The generation method and device of 3D virtual images |
CN108389253A (en) * | 2018-02-07 | 2018-08-10 | 盎锐(上海)信息科技有限公司 | Mobile terminal with modeling function and model generating method |
-
2018
- 2018-08-31 CN CN201811008355.XA patent/CN109089105B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160086304A1 (en) * | 2014-09-22 | 2016-03-24 | Ming Chuan University | Method for estimating a 3d vector angle from a 2d face image, method for creating face replacement database, and method for replacing face image |
US20180157901A1 (en) * | 2016-12-07 | 2018-06-07 | Keyterra LLC | Method and system for incorporating contextual and emotional visualization into electronic communications |
CN108305312A (en) * | 2017-01-23 | 2018-07-20 | 腾讯科技(深圳)有限公司 | The generation method and device of 3D virtual images |
CN107123160A (en) * | 2017-05-02 | 2017-09-01 | 成都通甲优博科技有限责任公司 | Simulation lift face system, method and mobile terminal based on three-dimensional image |
CN108389253A (en) * | 2018-02-07 | 2018-08-10 | 盎锐(上海)信息科技有限公司 | Mobile terminal with modeling function and model generating method |
Also Published As
Publication number | Publication date |
---|---|
CN109089105B (en) | 2020-06-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10116922B2 (en) | Method and system for automatic 3-D image creation | |
US9438878B2 (en) | Method of converting 2D video to 3D video using 3D object models | |
US9865055B2 (en) | Calibration for immersive content systems | |
US9094675B2 (en) | Processing image data from multiple cameras for motion pictures | |
EP3997662A1 (en) | Depth-aware photo editing | |
Matsuyama et al. | 3D video and its applications | |
CN104599317B (en) | A kind of mobile terminal and method for realizing 3D scanning modeling functions | |
US20140002612A1 (en) | Stereoscopic shooting device | |
JP2006053694A (en) | Space simulator, space simulation method, space simulation program and recording medium | |
CN107483845B (en) | Photographic method and its device | |
KR20150021522A (en) | Method and device for implementing stereo imaging | |
WO2019047985A1 (en) | Image processing method and device, electronic device, and computer-readable storage medium | |
CN107610080A (en) | Image processing method and device, electronic installation and computer-readable recording medium | |
CN107862718A (en) | 4D holographic video method for catching | |
KR101549929B1 (en) | Method and apparatus of generating depth map | |
CN108564654B (en) | Picture entering mode of three-dimensional large scene | |
CN108833890A (en) | Data processing equipment and method based on camera | |
CN107613224A (en) | Image processing method and device, electronic installation and computer-readable recording medium | |
KR101690256B1 (en) | Method and apparatus for processing image | |
US20220245885A1 (en) | Volumetric Imaging | |
CN109089105A (en) | Model generating means and method based on depth perception coding | |
CN104052990A (en) | Method and device for fully automatically converting two-dimension into three-dimension based on depth clue fusion | |
CN107644439A (en) | Image processing method and device, electronic installation and computer-readable recording medium | |
CN108810517A (en) | Image processor with monitoring function and method | |
JP7336871B2 (en) | All-dome video processing device and program |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230406 Address after: 518000 1101-g1, BIC science and technology building, No. 9, scientific research road, Maling community, Yuehai street, Nanshan District, Shenzhen, Guangdong Province Patentee after: Shenzhen Yujing Information Technology Co.,Ltd. Address before: 201703 No.206, building 1, no.3938 Huqingping Road, Qingpu District, Shanghai Patentee before: UNRE (SHANGHAI) INFORMATION TECHNOLOGY Co.,Ltd. |
|
TR01 | Transfer of patent right |