全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
电子学报  2013 

极低码率下的2D-3D人脸视频编解码

DOI: 10.3969/j.issn.0372-2112.2013.01.032, PP. 185-192

Keywords: 视频编解码,人脸运动跟踪,人脸动画,头发分析与建模

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对动态变化背景下的人脸视频编解码问题,该文提出了一种2D-3D混合编解码系统;具体包括:(1)基于多种观测信息,在线外观模型和粒子滤波的人脸三维运动跟踪;(2)结合参数模型与肌肉模型的3D人脸动画合成;(3)基于头发检测和3D头发模型的头发合成;(4)无缝地拼接前景的三维编解码结果和背景的二维编解码结果.在极低码率下,客观实验表明,该系统在编码效率和解码质量上有较好的综合优势.主观实验表明,该系统的解码结果在脸部具有较高的辨识度.

References

[1]  Forchheimer R.Image coding:from waveforms to animation[J].TASSP,1989,37(12):2008-2023.
[2]  Chai J X,Xiao J,Hodgins J.Vision-based control of 3D facial animation[A].Eurographics[C].Switzerland,Aire-la-Ville:ACM DL,2003.193-206.
[3]  Aizawa K,Harashima H,Saito T.Model-based analysis synthesis image coding(MBASIC) system for a person''s face[J].Image Communication,1989,1(2):139-152.
[4]  Q Wang,et al.Real-time bayesian 3-D pose tracking[J].TCSVT,2006,16(12):1533-1541.
[5]  J Strom.Model-Based Head Tracking and Coding[D].Sweden:Linkping University,2002.
[6]  J Ahlberg.Model-Based Coding:Extraction,Coding,and Evaluation of Face Model Parameters[D].Sweden:Linkping University,2002.
[7]  J Sung,T Kanade,D Kim.Pose robust face tracking by combining active appearance models and cylinder head models[J].IJCV,2008,80(2):260-274.
[8]  A D Jepson,et al.Robust online appearance models for visual tracking[J].TPAMI,2003,25(10):1296-1311.
[9]  F Dornaika,F Davoine.Simultaneous facial action tracking and expression recognition in the presence of head motion[J].IJCV,2008,76(3):257-281.
[10]  Z Wen,T Huang.Capturing subtle facial motions in 3d face tracking[A].ICCV[C].France,Nice:IEEE Xplore,2003.1343-1350.
[11]  K.Waters.A muscle model for animating three dimensional facial expression[J].Computer Graphics,1987,22(4):17-24.
[12]  Marcos S,Bermejo JGG,Zalama E.A realistic facial animation suitable for human-robot interfacing[A].ICIRS[C].Nice:IEEE Explore,2008.1-3.3810-3815.
[13]  杨晓辉.一种采用模型基辅助的混合视频编码方法[J].电路与系统学报,2002,7(2):35-38.Yang X H.A novel approach of model-aided hybrid coding[J].Journal Circuits and Systems.2002,7(2):35-38.(in Chinese)
[14]  J.Ahlberg.CANDIDE3-an Updated Parameterized Face[R].LiTH-ISY-R-2326,Department of Electrical Engineering,Linkping University,2001.1-16.
[15]  吴暾华,周昌乐.平面旋转人脸检测与特征定位方法研究[J].电子学报,2007,35(9):1714-1718.Wu T H,Zhou C L.Study on face detection under rotation in image plane and facial features localization[J].Acta Electronica Sinica,2007,35(9):1714-1718.(in Chinese)
[16]  M Kampmann.Automatic 3-D face mode adaption for model-based coding of videophone sequences[J].TCSVT,2002,12(3):172-182.
[17]  P Grassberger.The pruned-enriched rosenbluth method:simulations of theta polymers of chain length up to 1,000,000[J].Physical Review E,1997,56:3682-3693.
[18]  Levin A,Rav-Acha A,Lischinski D.Spectral matting[A].CVPR[C].Minneapolis,Minnesota,USA:IEEE Xplore,2007.1-8.
[19]  Hu Yuankui,et al.A Low-dimensional illumination space representation of human faces for arbitrary lighting conditions[A].ICPR[C].Hong Kong,China:IEEE,2006.1147-1150.
[20]  Liu YC,et al.A virtual teleconferencing system based on face detection and 3D animation in a low bandwidth environment[J].JIST,2010,20(4):323-332.
[21]  普波.基于视频的三维人脸动画驱动的设计与实现[D].电子科技大学,2010.Pu B.Design of 3D Facial Animation Based on Video[D].University of Electronic Science and Technology,2010.(in Chinese)
[22]  B Moghaddam,et al.An automatic system for model based coding of faces[A].DSC[C].UT,Snowbird:IEEE Explore,1995.568-573.
[23]  S.Gokturk et al.A data-driven model for monocular face tracking[A].ICCV[C].Vancouver,BC:IEEE Xplore,2001.701-708.
[24]  Wei Zhang,et al.Real Time feature based 3-D deformable face tracking[A].ECCV[C].Berlin,Heidelberg:Springer-Verlag,2008.720-732.
[25]  L Vacchetti,et al.Stable real-time 3D tracking using online and offline information[J].PAMI,2004,26(10):1385-1391.
[26]  Wei-Kai Liao,et al.Integrating multiple visual cues for robust 3d face tracking[A].AMFG[C].Berlin,Heidelberg:Springer-Verlag,2007.109-123.
[27]  M L Cascia,et al.Fast,reliable head tracking under varying illumination:An approach based on registration of texture mapped 3D models[J].TPAMI,2000,22(4):322-336.
[28]  I Matthews,et al.2D vs 3D deformable face models:Representational power,construction,and real-time fitting[J].IJCV,2007,75(1):93-113.
[29]  Lui YM,et al.Adaptive appearance model and condensation algorithm for robust face tracking[J].TSMC Part A,2010,40(3):437-448.
[30]  S Zhou,et al.Visual tracking and recognition using appearance-adaptive models in particle filters[J].TIP,2004,13(11):1491-1506.
[31]  Tim K Marks,et al.Tracking motion,deformation,and texture using conditionally gaussian processes[J].TPAMI,2010,32(2):348-363.
[32]  F I Parke,K Waters.Computer Facial Animation[M].Wellesley,MA:A K Peters,1996.1-365.
[33]  Wang W M,et al.A physically-based modeling and simulation framework for facial animation[A].ICIG[C].Xi''an,Shanxi:IEEE Explore,2009.521-526.
[34]  Volker Blanz,et al.Reanimating faces in images and video[J].Computer Graph,2003,22(3):641-650.
[35]  张黎.真实感三维头发的建模及动态模拟算法研究[D].浙江大学,2010.Zhang L.Research on 3D Hair Modeling and Dynamic Simulation[D].University of Zhejiang,2010.(in Chinese)
[36]  Peter Eisert,et al.Model-aided coding:a new approach to incorporate facial animation into motion-compensated video coding[J].TCSVT,2000,10(3):344-358.
[37]  Koray Balc,et al.Xface open source project and SMIL-agent scripting language for creating and animating embodied conversational agents[A].ICM[C].Augsburg,Germany:ACM DL,2007.1013-1016.
[38]  吴证,周越,杜春华等.彩色图像人脸特征点定位算法研究[J].电子学报,2008,36(2):309-313.Wu Z,Zhou Y,et al.Research on facial feature points extraction in color images[J].Acta Electronica Sinica,2008,36(2):309-313.(in Chinese)
[39]  薛峰,丁晓青.基于形状匹配变形模型的三维人脸重构[J].电子学报,2006,34(10):1896-1899.Xue F,Ding X Q.3D reconstruction of human face based on shape match morphing model[J].Acta Electronica Sinica,2006,34(10):1896-1899.(in Chinese)
[40]  Yaser Yacoob,Larry S.Davis.Detection and analysis of hair[J].TPAMI,2006,28(7):1164-1169.
[41]  Hu Yuankui,et al.Reconstruction of 3D face from a single 2D image for face recognition[A].International Workshop on VSPETS[C].San Diego,California USA:IEEE Xplore,2005.217-222.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133