CN104778750A - Facial expression capturing system and implementation method - Google Patents
Facial expression capturing system and implementation method Download PDFInfo
- Publication number
- CN104778750A CN104778750A CN201510174032.8A CN201510174032A CN104778750A CN 104778750 A CN104778750 A CN 104778750A CN 201510174032 A CN201510174032 A CN 201510174032A CN 104778750 A CN104778750 A CN 104778750A
- Authority
- CN
- China
- Prior art keywords
- camera
- helmet
- photo
- wearer
- face
- 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 facial expression capturing system. The facial expression capturing system is characterized by comprising a helmet (1), camera supporting rods (2), a camera (3) and a data transmission line (4), wherein the camera supporting rods (2) are arranged on two sides of the helmet (1) and are connected with the helmet (1) through clamps; the camera (3) is arranged at the front end of the helmet (1), is connected with the helmet (1) through the camera supporting rods (2) and is suspended in front of the helmet (1); the data transmission line (4) is directly connected with the camera (3). The facial expression capturing system has the benefits that the accurate movement of the head and the facial expression can be automatically positioned and tracked; the face does not need to be calibrated by any identification points or paint marks, the identification points are automatically added, and a vivid facial animation can be quickly created after a user wears the corresponding helmet; the facial animation can be easily integrated to any manufacturing flow and is in expression association with a role of three-dimensional animation software, and the facial expression animation is adjusted in real time.
Description
Technical field
The present invention relates to technical field of computer vision, especially a kind of facial expression capture system and implementation method.
Background technology
Facial expression is the most direct channel of emotional expression, is a kind of very important non-verbal communication means.Artists often by the description to character face's expression, show mood and the emotion of personage's heart.In today that computer graphics techniques makes rapid progress, motion capture technology has brought the performance of performer into virtual world, allows three-dimensional role gradually enter into screen.
Summary of the invention
For solving the problems of the technologies described above, the invention provides a kind of facial expression capture system, comprising the helmet 1, camera pole 2, camera 3 and data line 4; Be provided with camera pole 2 in the both sides of the helmet 1, camera pole 2 is connected with the helmet 1 by jig; Be provided with camera 3 in the front end of the helmet 1, camera 3 to be connected with the helmet 1 by camera pole 2 and to be suspended at the helmet 1 front; Data line 4 is directly connected with camera 3.
Preferably, the material of the helmet 1 is light-high-strength resin material.
Preferably, the helmet 1 inside is also provided with the liner of fitting with head curve form.
Preferably, the material of camera pole 2 is high-strength aluminum alloy.
The implementation method that facial expression catches, comprises the steps:
(1) according to wearer's head size adjustment helmet size, check that computer hardware generates machine number, and by machine number application License, catch software with corresponding face and bind;
(2) adjusting helmet camera lens, catches the real-time action data of wearer by the helmet;
(3) head modeling is carried out to character; The front of camera shooting wearer and side face photograph, import wearer's photo, uses Facial Studio to carry out picture match modeling;
(4) opening Motionbuilder by MaskaradRT software activation is connected to computer by data line by camera, is regulated the position of camera and wearer's face by the image showing camera; Wearer's face is all presented in picture, the position of fixing camera, the model built up is imported in Motionbuilder, by MaskaradRT, the expression passage of model is associated one by one with model in (3);
(5) after association well, wearer is connected in real time with model, the expression of wearer and the expression synchronization of model; Carry out establishment face by MaskaradRT and catch a cloud, carry out the seizure recording that expression is caught in face; The point cloud file recorded is imported in three-dimensional software and binds.
Preferably, in step (3), the concrete steps of modeling are:
The first step: prepare head photographic material.Need front and each one of side photo, for carrying out the modeling of photo coupling.Ensure that personage is motionless and change the position of camera, time taking pictures in front, requiring the character face's image in view finder to try one's best maintenance level and symmetry.
Second step: use Facial Studio to Load Image, carries out the modeling of photo coupling.
A. on disk, find ready personage's full face, on the left side region, be loaded into personage front photograph, be loaded into side portrait according in region in side on the right with method;
B. click and drag the demarcation strip in the middle of preview view and photo match views, making photo size and active view Auto-matching;
C. pull the Green triangle in photo match views, mobile green structure lines, personage's head in photo lived by frame;
D. click the blue reference mark on dragging structure line, the various piece of location structure line, make structure lines mate position corresponding in photo as far as possible;
E., in photo match views, after the operation of structure lines contraposition is all completed to front and side photo, in preview view, the shape of head mould is seen;
F., in distortion on the right and parameter tuned plate region, find Creation group, select High Resolution, MediumResolution, Low Resolution one of them, set the precision of current three-dimensional head portrait model to adapt to different needs;
G. head portrait makes complete being just output in other Three-dimensional Animation Softwares and makes role animation.
Beneficial effect of the present invention is: automatically location and follow the tracks of the precise motion of head and facial expression, and carry out face without the need to any identification point or painting sign and demarcate, automatic powder adding adds identification point, need to bring the corresponding helmet just can fast creation FA Facial Animation true to nature; Can be integrated into easily in any Making programme, that carries out expressing one's feelings with the role of Three-dimensional Animation Software associates, and regulates facial expression animation in real time.
Accompanying drawing explanation
Fig. 1 is hardware structure diagram of the present invention.
Fig. 2 is the correspondence position schematic diagram of of the present invention some cloud and face.
Fig. 3 is the expression tunnel name schematic diagram of corresponding point cloud of the present invention.
Fig. 4 is method flow diagram of the present invention.
Embodiment
As shown in Figure 1, a kind of facial expression capture system, comprises the helmet 1, camera pole 2, camera 3 and data line 4; Be provided with camera pole 2 in the both sides of the helmet 1, camera pole 2 is connected with the helmet 1 by jig; Be provided with camera 3 in the front end of the helmet 1, camera 3 to be connected with the helmet 1 by camera pole 2 and to be suspended at the helmet 1 front; Data line 4 is directly connected with camera 3.
The helmet 1 is that light-high-strength resin material makes, and alleviate the weight of wearer's head, the liner of comfortable softness is posted in the inside, comfortable wearing and ensure that the helmet 1 and wearer's geo-stationary, can not misplace; Camera pole 2 is made by high-strength aluminum alloy, has increased substantially physical strength and the skin hardness of pole, and still remains the lightweight characteristic of pole, repeatedly uses and also can not make pole bending; Camera 3 is high definition camera, can record 1080P HD high-definition data, real-time Transmission 720P HD data, ensures the image quality of shooting and the accuracy of data calculating.
The implementation method that facial expression catches, comprises the steps:
(1) according to wearer's head size adjustment helmet size, check that computer hardware generates machine number, and by machine number application License, catch software with corresponding face and bind;
(2) adjusting helmet camera lens, catches the real-time action data of wearer by the helmet;
(3) head modeling is carried out to character; The front of camera shooting wearer and side face photograph, import wearer's photo, uses Facial Studio to carry out picture match modeling;
(4) opening Motionbuilder by MaskaradRT software activation is connected to computer by data line by camera, is regulated the position of camera and wearer's face by the image showing camera; Wearer's face is all presented in picture, the position of fixing camera, the model built up is imported in Motionbuilder, by MaskaradRT, the expression passage of model is associated one by one with model in (3);
(5) after association well, wearer is connected in real time with model, the expression of wearer and the expression synchronization of model; Carry out establishment face by MaskaradRT and catch a cloud, carry out the seizure recording that expression is caught in face; The point cloud file recorded is imported in three-dimensional software and binds.
The concrete steps of modeling are:
The first step: prepare head photographic material.Need front and each one of side photo, for carrying out the modeling of photo coupling.Will note 2 points when taking pictures: the first, ensure that personage is motionless as far as possible and change the position of camera, taking pictures like this is that light information in order to ensure being photographed character face is consistent, and seam appears in the character face's pinup picture avoiding Facial Studio to calculate; The second, time taking pictures in front, require the character face's image in view finder to try one's best maintenance level and symmetry, this is the accuracy in order to improve the modeling of photo coupling equally.
Second step: use Facial Studio to Load Image, carries out the modeling of photo coupling.
A. select front, the left side according to region, click upper left corner button, open any browser, disk finds ready personage's full face, is loaded into, and is loaded into side portrait in side on the right with method according in region;
B. click and drag the demarcation strip in the middle of preview view and photo match views, photo match views is become and handled easily, clicking the button above photo match views, photo size and active view Auto-matching can be made;
C. pull the Green triangle in photo match views, mobile green structure lines, make its frame of trying one's best live personage's head in photo;
D. click the blue reference mark on dragging structure line, the various piece of location structure line, make structure lines mate position corresponding in photo as far as possible;
E., in photo match views, after the operation of structure lines contraposition is all completed to front and side photo, the shape of head mould can be seen inside in preview view;
F., in distortion on the right and parameter tuned plate region, find Creation group, select High Resolution, MediumResolution, Low Resolution one of them, they can set the precision of current three-dimensional head portrait model to adapt to different needs;
G. head portrait makes complete being just output in other Three-dimensional Animation Softwares and makes role animation.
Although the present invention illustrates with regard to preferred implementation and describes, only it will be understood by those of skill in the art that otherwise exceed claim limited range of the present invention, variations and modifications can be carried out to the present invention.
Claims (6)
1. a facial expression capture system, is characterized in that, comprises the helmet (1), camera pole (2), camera (3) and data line (4); Be provided with camera pole (2) in the both sides of the helmet (1), camera pole (2) is connected with the helmet (1) by jig; Be provided with camera (3) in the front end of the helmet (1), camera (3) to be connected with the helmet (1) by camera pole (2) and to be suspended at the helmet (1) front; Data line (4) is directly connected with camera (3).
2. the system as claimed in claim 1, is characterized in that, the material of the helmet (1) is light-high-strength resin material.
3. system as claimed in claim 2, is characterized in that, the helmet (1) inside is also provided with the liner of fitting with head curve form.
4. the system as claimed in claim 1, is characterized in that, the material of camera pole (2) is high-strength aluminum alloy.
5. an implementation method for facial expression seizure, is characterized in that, comprise the steps:
(1) according to wearer's head size adjustment helmet size, check that computer hardware generates machine number, and by machine number application License, catch software with corresponding face and bind;
(2) adjusting helmet camera lens, catches the real-time action data of wearer by the helmet;
(3) head modeling is carried out to character; The front of camera shooting wearer and side face photograph, import wearer's photo, uses Facial Studio to carry out picture match modeling;
(4) opening Motionbuilder by MaskaradRT software activation is connected to computer by data line by camera, is regulated the position of camera and wearer's face by the image showing camera; Wearer's face is all presented in picture, the position of fixing camera, the model built up is imported in Motionbuilder, by MaskaradRT, the expression passage of model is associated one by one with model in (3);
(5) after association well, wearer is connected in real time with model, the expression of wearer and the expression synchronization of model; Carry out establishment face by MaskaradRT and catch a cloud, carry out the seizure recording that expression is caught in face; The point cloud file recorded is imported in three-dimensional software and binds.
6. method as claimed in claim 5, is characterized in that, in step (3), the concrete steps of modeling are:
The first step: prepare head photographic material; Front and each one of side photo, for carrying out the modeling of photo coupling; Ensure that personage is motionless and change the position of camera, time taking pictures in front, requiring the character face's image in view finder to try one's best maintenance level and symmetry;
Second step: use Facial Studio to Load Image, carries out the modeling of photo coupling;
A. on disk, find ready personage's full face, on the left side region, be loaded into personage front photograph, be loaded into side portrait according in region in side on the right with method;
B. click and drag the demarcation strip in the middle of preview view and photo match views, making photo size and active view Auto-matching;
C. pull the Green triangle in photo match views, mobile green structure lines, personage's head in photo lived by frame;
D. click the blue reference mark on dragging structure line, the various piece of location structure line, make structure lines mate position corresponding in photo as far as possible;
E., in photo match views, after the operation of structure lines contraposition is all completed to front and side photo, in preview view, the shape of head mould is seen;
F., in distortion on the right and parameter tuned plate region, find Creation group, select High Resolution, MediumResolution, Low Resolution one of them, set the precision of current three-dimensional head portrait model to adapt to different needs;
G. head portrait makes complete being just output in other Three-dimensional Animation Softwares and makes role animation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510174032.8A CN104778750B (en) | 2015-04-13 | 2015-04-13 | A kind of facial expression captures system and implementation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510174032.8A CN104778750B (en) | 2015-04-13 | 2015-04-13 | A kind of facial expression captures system and implementation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104778750A true CN104778750A (en) | 2015-07-15 |
| CN104778750B CN104778750B (en) | 2018-12-18 |
Family
ID=53620193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510174032.8A Active CN104778750B (en) | 2015-04-13 | 2015-04-13 | A kind of facial expression captures system and implementation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104778750B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105411076A (en) * | 2015-12-25 | 2016-03-23 | 天津市数字道科技有限责任公司 | Helmet for facial expression capture system |
| WO2018082692A1 (en) * | 2016-11-07 | 2018-05-11 | Changchun Ruixinboguan Technology Development Co., Ltd. | Systems and methods for interaction with application |
| CN108140105A (en) * | 2015-09-29 | 2018-06-08 | 比纳里虚拟现实技术有限公司 | Head-mounted display with countenance detectability |
| CN108139663A (en) * | 2016-03-03 | 2018-06-08 | 萨利赫·伯克·伊尔汉 | Smile mirror |
| CN110263672A (en) * | 2019-05-30 | 2019-09-20 | 量子动力（深圳）计算机科技有限公司 | A kind of binocular 3D grid high-fidelity human face expression capture system |
| CN113418121A (en) * | 2021-06-22 | 2021-09-21 | 苏州睿东科技开发有限公司 | Vlog shooting equipment and assembling and using method |
| CN115546868A (en) * | 2022-10-25 | 2022-12-30 | 湖南芒果无际科技有限公司 | Facial animation acquisition apparatus, method and readable storage medium |
Citations (3)
| 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 |
| US20100079664A1 (en) * | 2008-09-29 | 2010-04-01 | Imagemovers Digital Llc | Mounting and bracket for an actor-mounted motion capture camera system |
| CN102521464A (en) * | 2011-12-26 | 2012-06-27 | 北京航空航天大学 | Digital enterprise lean manufacturing interactive application (DELMIA)-environment-based virtual human control method for immersive virtual maintenance simulation system |
-
2015
- 2015-04-13 CN CN201510174032.8A patent/CN104778750B/en active Active
Patent Citations (3)
| 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 |
| US20100079664A1 (en) * | 2008-09-29 | 2010-04-01 | Imagemovers Digital Llc | Mounting and bracket for an actor-mounted motion capture camera system |
| CN102521464A (en) * | 2011-12-26 | 2012-06-27 | 北京航空航天大学 | Digital enterprise lean manufacturing interactive application (DELMIA)-environment-based virtual human control method for immersive virtual maintenance simulation system |
Non-Patent Citations (2)
| Title |
|---|
| YC2524: ""Facial Studio 实例教程-通过照片匹配快速建立头部模型"", 《HTTPS://WENKU.BAIDU.COM/VIEW/DED91506B52ACFC789EBC920.HTML》 * |
| 网易数码: "Faceware无标记点面部表情捕捉系统来袭", 《HTTP://DIGI.163.COM/13/1121/14/9E79VVEP001664LU.HTML》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108140105A (en) * | 2015-09-29 | 2018-06-08 | 比纳里虚拟现实技术有限公司 | Head-mounted display with countenance detectability |
| CN105411076A (en) * | 2015-12-25 | 2016-03-23 | 天津市数字道科技有限责任公司 | Helmet for facial expression capture system |
| CN108139663A (en) * | 2016-03-03 | 2018-06-08 | 萨利赫·伯克·伊尔汉 | Smile mirror |
| WO2018082692A1 (en) * | 2016-11-07 | 2018-05-11 | Changchun Ruixinboguan Technology Development Co., Ltd. | Systems and methods for interaction with application |
| CN110263672A (en) * | 2019-05-30 | 2019-09-20 | 量子动力（深圳）计算机科技有限公司 | A kind of binocular 3D grid high-fidelity human face expression capture system |
| CN113418121A (en) * | 2021-06-22 | 2021-09-21 | 苏州睿东科技开发有限公司 | Vlog shooting equipment and assembling and using method |
| CN113418121B (en) * | 2021-06-22 | 2023-10-13 | 苏州睿东科技开发有限公司 | Volg shooting equipment and assembling and using method |
| CN115546868A (en) * | 2022-10-25 | 2022-12-30 | 湖南芒果无际科技有限公司 | Facial animation acquisition apparatus, method and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104778750B (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104778750A (en) | Facial expression capturing system and implementation method | |
| US10127945B2 (en) | Visualization of image themes based on image content | |
| US9041899B2 (en) | Digital, virtual director apparatus and method | |
| US9262696B2 (en) | Image capture feedback | |
| EP2225607B1 (en) | Guided photography based on image capturing device rendered user recommendations | |
| EP2629267A2 (en) | Real-time compositing of live recording-based and computer graphics-based media streams | |
| US10523916B2 (en) | Modifying images with simulated light sources | |
| CN107749952B (en) | Intelligent unmanned photographing method and system based on deep learning | |
| CN106375662A (en) | Photographing method and device based on double cameras, and mobile terminal | |
| US9928658B2 (en) | Overlay for camera field of vision | |
| US20130162628A1 (en) | System, method and apparatus for rapid film pre-visualization | |
| CN103369238B (en) | Image creating device and image creating method | |
| CN104599317A (en) | Mobile terminal and method for achieving 3D (three-dimensional) scanning modeling function | |
| KR20170027266A (en) | Image capture apparatus and method for operating the image capture apparatus | |
| CN108600729A (en) | Dynamic 3D models generating means and image generating method | |
| CN106791347A (en) | A kind of image processing method, device and the mobile terminal using the method | |
| CN106663340A (en) | Method and device for editing a facial image | |
| CN110611768B (en) | Multiple exposure photographic method and device | |
| CN111598983A (en) | Animation system, animation method, storage medium, and program product | |
| CN105740450A (en) | Multi-Kinect based 3D human body posture database construction method | |
| CN108010061A (en) | A kind of deep learning light stream method of estimation instructed based on moving boundaries | |
| CN110177216A (en) | Image processing method, device, mobile terminal and storage medium | |
| US11367210B1 (en) | Smoothly changing a focus of a camera between multiple target objects | |
| CN103957360A (en) | Control method and device with high-speed particle follow shooting function | |
| Zhang et al. | Face animation making method based on facial motion capture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100190, room 10, building 3, building No. 1003, Zijin digital garden, West Haidian District, Beijing, Wudaokou Applicant after: BEIJING DISON DIGITAL ENTERTAINMENT TECHNOLOGY CO., LTD. Address before: 100043, 4 floor, building 3, Shijingshan science and Technology Museum, Beijing, Shijingshan District Applicant before: Beijing Dison Animation Technology Co., Ltd. |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |