CN108108725A - A kind of personage head based on ultra high-definition photo and facial expression data acquisition platform - Google Patents
A kind of personage head based on ultra high-definition photo and facial expression data acquisition platform Download PDFInfo
- Publication number
- CN108108725A CN108108725A CN201810056369.2A CN201810056369A CN108108725A CN 108108725 A CN108108725 A CN 108108725A CN 201810056369 A CN201810056369 A CN 201810056369A CN 108108725 A CN108108725 A CN 108108725A
- Authority
- CN
- China
- Prior art keywords
- unit
- cpu element
- data acquisition
- facial expression
- expression data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10008—Still image; Photographic image from scanner, fax or copier
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Abstract
The present invention provides a kind of personage head based on ultra high-definition photo and facial expression data acquisition platform, including multi-cam control system, illumination system, control unit, preview unit, CPU element, GPU units, power supply unit and photographic imagery unit；Illumination system controls multi-cam control system to be provided in illumination system under sufficient illumination assistance, by the multi-faceted comprehensive digital scan to personage head and generate image, and image information is sent to preview unit in a manner that infinite data transmits, image information is carried out calculating analysis by preview unit through CPU element collaboration GPU units to image, power supply unit can be CPU element, GPU units provide electric energy, pass through CPU element, GPU units calculate analysis generation 3D number of people images, the framework standard of real human body head portrait of the present invention, then the three dimensional point cloud of equipment acquisition human body head portrait is obtained by three-dimensional datas such as scanner and video cameras, by computer data are carried out with the 3D geometrical models that processing obtains human body head portrait again.
Description
Technical field
The invention belongs to face data acquisition technique field more particularly to a kind of personage head based on ultra high-definition photo with
Facial expression data acquisition platform.
Background technology
The present invention provides a set of quick personage head based on ultra high-definition photo and facial expression data acquisition platform, collection
Texture shooting, point cloud is rebuild, generation model is in the advanced making assembly line of one, which serves primarily in visual effect row
Industry.
Three-dimensional modeling is a basic problem in computer vision and field of Computer Graphics, and face is special by it
Some generalities and ease for use become the research object that numerous experts and scholars carry out three-dimensional modeling.The modeling of human body head portrait is exactly handle
Then the framework standard of real human body head portrait obtains equipment by three-dimensional datas such as scanner and video cameras and obtains human body head portrait
Three dimensional point cloud, then by computer to data carry out processing obtain human body head portrait 3D geometrical models.
Therefore, a kind of personage head based on ultra high-definition photo of invention seems with facial expression data acquisition platform and very must
It will.
The content of the invention
For above-mentioned technical problem, the present invention provides a kind of based on the personage head of ultra high-definition photo and facial expression data
Acquisition platform.
A kind of personage head based on ultra high-definition photo and facial expression data acquisition platform, which is characterized in that this is based on
The personage head of ultra high-definition photo includes multi-cam control system, illumination system, control with facial expression data acquisition platform
Unit, preview unit, CPU element, GPU units, power supply unit and photographic imagery unit；Illumination system control multi-cam control
System is provided in illumination system under sufficient illumination assistance, by the multi-faceted comprehensive digital scan to personage head and is generated
Image, and image information is sent to preview unit in a manner that infinite data transmits, preview unit is mono- through CPU by image information
Member collaboration GPU units carry out image calculating analysis, and power supply unit can provide electric energy for CPU element, GPU units, mono- by CPU
Member, GPU units calculate analysis generation 3D number of people images.
Preferably, the illumination system is formed using the surrounding of scanning platform and multiple LED illumination lamps at top is dispersed in
One lighting environment without shadow.
Preferably, the photo of automatic copy shooting is renamed to unified storage catalogue, and according to device numbering.
Compared with prior art, the present invention has the advantages that：The framework standard of real human body head portrait of the present invention,
Then obtain equipment by three-dimensional datas such as scanner and video cameras and obtain the three dimensional point cloud of human body head portrait, then pass through calculating
Machine carries out data the 3D geometrical models that processing obtains human body head portrait.
Description of the drawings
Fig. 1 is structure principle chart of the present invention.
In figure：
1- faces, 2- capture point camera system, 3- wireless data sending devices, 4- memories, 5- digital independents device, 6- and capture
Point location camera system.
Specific embodiment
The present invention is described further below in conjunction with attached drawing：
Embodiment：
As shown in Figure 1, the present invention provides a kind of personage head based on ultra high-definition photo and facial expression data acquisition platform,
It is characterized in that, personage head that should be based on ultra high-definition photo includes multi-cam control system with facial expression data acquisition platform
System 1, illumination system 2, control unit 3, preview unit 4, CPU element 5, GPU units 6, power supply unit 7 and photographic imagery unit 8；
Illumination system 2 controls multi-cam control system 1 to be provided in illumination system 2 under sufficient illumination assistance, by multi-faceted to people
The comprehensive digital scan on object head simultaneously generates image, and image information is sent to preview list in a manner that infinite data transmits
Member 4, image information is cooperateed with GPU units 6 to carry out calculating analysis to image by preview unit 4 through CPU element 5, and power supply unit 7 can be
CPU element 5, GPU units 6 provide electric energy, and analysis generation 3D number of people images, illumination system are calculated by CPU element 5, GPU units 6
System 2 forms a lighting environment without shadow, automatically using the surrounding of scanning platform and multiple LED illumination lamps at top is dispersed in
The photo of copy shooting is renamed to unified storage catalogue, and according to device numbering.
Operation principle
The dependence photogrammetric technology of multi-cam control system 1 that the present invention is formed using multiple high-definition digital cameras is come into pedestrian
The digital scan on object head calculates depth by searching for the sharing feature between multiple photos through CPU element 5, GPU units 6,
Virtual camera, that is, photographic imagery unit 8 of three dimensions is aligned, and generates digital spot cloud according to depth data, is innovated
Property introduce GPU units 6, traditional single computing model using CPU element 5 is breached, using Intel Xeon cores
With cooperateing with for NVIDIA Tesla speedup computation techniques, allowing CPU element 5 and GPU units 6, Each performs its own functions, and CPU element 5 is mainly held
It carries on a shoulder pole the logic selection being more good at, judge the responsibility redirected etc., and GPU units 6 then full-time computation-intensive, highly-parallel
Evaluation work so that computing resource is reasonably distributed, calculate power fully discharged.
Using technical solutions according to the invention or those skilled in the art under the inspiration of technical solution of the present invention,
Similar technical solution is designed, and reaches above-mentioned technique effect, is to fall into protection scope of the present invention.
Claims (3)
1. a kind of personage head based on ultra high-definition photo and facial expression data acquisition platform, which is characterized in that should be based on super
The personage head of high definition photo includes multi-cam control system with facial expression data acquisition platform（1）, illumination system（2）、
Control unit（3）, preview unit（4）, CPU element（5）, GPU units（6）, power supply unit（7）With photographic imagery unit（8）；Light
Lighting system（2）Control multi-cam control system（1）In illumination system（2）It provides under sufficient illumination assistance, by multi-faceted
Comprehensive digital scan to personage head simultaneously generates image, and image information is sent in a manner that infinite data transmits pre-
Look at unit（4）, preview unit（4）By image information through CPU element（5）Cooperate with GPU units（6）Calculating analysis is carried out to image,
Power supply unit（7）It can be CPU element（5）, GPU units（6）Electric energy is provided, passes through CPU element（5）, GPU units（6）It calculates and divides
Analysis generation 3D number of people images.
2. the multi-cam control system（1）A kind of personage head based on ultra high-definition photo and facial expression data acquisition are flat
Platform, which is characterized in that the illumination system（2）Using the multiple LED illumination lamps for the surrounding and top for being dispersed in scanning platform, shape
Into a lighting environment without shadow.
3. a kind of personage head based on ultra high-definition photo and facial expression data acquisition platform, which is characterized in that automatic copy
The photo of shooting is renamed to unified storage catalogue, and according to device numbering.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810056369.2A CN108108725A (en) | 2018-01-20 | 2018-01-20 | A kind of personage head based on ultra high-definition photo and facial expression data acquisition platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810056369.2A CN108108725A (en) | 2018-01-20 | 2018-01-20 | A kind of personage head based on ultra high-definition photo and facial expression data acquisition platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108108725A true CN108108725A (en) | 2018-06-01 |
Family
ID=62219175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810056369.2A Pending CN108108725A (en) | 2018-01-20 | 2018-01-20 | A kind of personage head based on ultra high-definition photo and facial expression data acquisition platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108108725A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114339065A (en) * | 2022-01-13 | 2022-04-12 | 北京大橘大栗文化传媒有限公司 | Nine-point high-precision face data acquisition method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101310289A (en) * | 2005-08-26 | 2008-11-19 | 索尼株式会社 | Capturing and processing facial motion data |
| CN104123562A (en) * | 2014-07-10 | 2014-10-29 | 华东师范大学 | Human body face expression identification method and device based on binocular vision |
| CN104811650A (en) * | 2014-01-26 | 2015-07-29 | 吴健辉 | Image acquisition system |
| CN106611426A (en) * | 2015-10-16 | 2017-05-03 | 灵然创智（天津）动画科技发展有限公司 | 3D (Three-dimensional) facial animation real-time capture technology based on depth camera |
| CN106851070A (en) * | 2017-03-13 | 2017-06-13 | 北京智造宝科技有限公司 | A kind of three dimensional face scanner with monitoring camera |
-
2018
- 2018-01-20 CN CN201810056369.2A patent/CN108108725A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101310289A (en) * | 2005-08-26 | 2008-11-19 | 索尼株式会社 | Capturing and processing facial motion data |
| CN104811650A (en) * | 2014-01-26 | 2015-07-29 | 吴健辉 | Image acquisition system |
| CN104123562A (en) * | 2014-07-10 | 2014-10-29 | 华东师范大学 | Human body face expression identification method and device based on binocular vision |
| CN106611426A (en) * | 2015-10-16 | 2017-05-03 | 灵然创智（天津）动画科技发展有限公司 | 3D (Three-dimensional) facial animation real-time capture technology based on depth camera |
| CN106851070A (en) * | 2017-03-13 | 2017-06-13 | 北京智造宝科技有限公司 | A kind of three dimensional face scanner with monitoring camera |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114339065A (en) * | 2022-01-13 | 2022-04-12 | 北京大橘大栗文化传媒有限公司 | Nine-point high-precision face data acquisition method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021042277A1 (en) | Method for acquiring normal vector, geometry and material of three-dimensional object employing neural network | |
| Shan et al. | The visual turing test for scene reconstruction | |
| CN104424662B (en) | Stereo scanning device | |
| CN101452582B (en) | Method and device for implementing three-dimensional video specific action | |
| CN106228507A (en) | A kind of depth image processing method based on light field | |
| WO2018075053A1 (en) | Object pose based on matching 2.5d depth information to 3d information | |
| EP3398168A1 (en) | A method and system for real-time 3d capture and live feedback with monocular cameras | |
| CN109074369A (en) | Image characteristic combination for the Object identifying based on image | |
| CN113514008B (en) | Three-dimensional scanning method, three-dimensional scanning system, and computer-readable storage medium | |
| Jeni et al. | The first 3d face alignment in the wild (3dfaw) challenge | |
| CN106462943A (en) | Aligning panoramic imagery and aerial imagery | |
| CN109816784A (en) | The method and system and medium of three-dimensionalreconstruction human body | |
| US20200057778A1 (en) | Depth image pose search with a bootstrapped-created database | |
| CN108780319A (en) | Oftware updating method, system, mobile robot and server | |
| WO2019157989A1 (en) | Biological feature 3d data acquisition method and biological feature 3d data recognition method | |
| WO2022021782A1 (en) | Method and system for automatically generating six-dimensional posture data set, and terminal and storage medium | |
| CN109242898A (en) | A kind of three-dimensional modeling method and system based on image sequence | |
| Pillai et al. | The 2nd 3D Face Alignment in the Wild Challenge (3DFAW-Video): Dense Reconstruction From Video. | |
| Gattet et al. | A versatile and low-cost 3D acquisition and processing pipeline for collecting mass of archaeological findings on the field | |
| CN108108725A (en) | A kind of personage head based on ultra high-definition photo and facial expression data acquisition platform | |
| CN113065506B (en) | Human body posture recognition method and system | |
| CN112330753B (en) | Target detection method of augmented reality system | |
| CN115442519B (en) | Video processing method, apparatus and computer readable storage medium | |
| Priya et al. | 3DYOLO: Real-time 3D Object Detection in 3D Point Clouds for Autonomous Driving | |
| Dikovski et al. | Structure from motion obtained from low quality images in indoor environment |
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 |