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...

基于非线性流形学习的3维人体运动合成

DOI: 10.11834/jig.20100613

Keywords: 流形学习,运动合成,运动语义

Full-Text   Cite this paper   Add to My Lib

Abstract:

为了实现3维人体运动的有效合成,提出了一种基于非线性流形学习的3维人体运动合成框架及算法,并可应用于方便、快捷、用户可控的3维人体运动合成。该合成算法框架先采用非线性流形降维方法将高维运动样本映射到低维流形上,同时求解其本征运动语义参数空间的表达,然后将用户在低维运动语义参数空间中交互生成的样本通过逆向映射重建得到具有新运动语义特征的3维运动序列。实验结果表明该方法不仅能够对运动物理参数(如特定关节的运动位置、物理运动特征)进行较为精确的控制,还可用于合成具有高层运动语义(运动风格)的新运动数据。与现有运动合成方法比较,该方法具有用户可控、交互性强等优点,能够应用于常见3维人体运动数据的高效生成。

References

[1]  Park Sang II,Shin Hyun Joon,Kim Tae Hoon,et al.On-line motion blending for real-time locomotion generation[J].Computer Animation and Virtual Worlds,2004,15(3-4):125-138.
[2]  Belkin Mikhail,Niyogi Partha.Laplacian eigenmaps for dimensionality reduction and data representation[J].Neural Computation,2003,15(6):1373-1396.
[3]  He Xiaofei,Niyogi Partha.Locality preserving projections[J].Advances in Neural Information Processing Systems,2003,16:153-160.
[4]  Rose Charles,Bodenheiraer Bobby,Cohen Michael F.Verbs and adverbs:Multidimensional motion interpolation using radial basis functions[J].IEEE Computer Graphics and Applications,1998,18(5):32-40.
[5]  Rose Charles,Guenter Brian,Bodenheimer Bobby,et al.Efficient generation of motion transitions using spacetime constraints[C]//Proceedings of the 23rd Annual Conference on Computer Graphics and Tnteractive Techniques.New York:ACM Press,1996:147-154.
[6]  Menardais Stephane,Multon Franck,Kulpa Richard,et al.Motion blending for real-time animation while accounting for the environment[C] //Proceedings of the International Conference on Computer Graphics,Los Alamitos CA,USA:IEEE Computer Society,2004:156-159.
[7]  Kovar Lucas,Gleicher Michael.Motion graphs[J].ACM Transactions on Graphics(TOG),2002,21(3):473-482.
[8]  Gleicher Michael,Shin Hyun Joon,Kovar Lucas,et al.Snap-together motion:assembling run-time animations[C]// Proceeding of ACM SIGGRAPH 2003.New York:ACM Press,2003:181-188.
[9]  Xiao Jun,Zhuang Yueting,Wu Fei.Getting distinct movements from motion capture data[C] //Proceedings of Computer Animation and Social Agents.Geneva,Switzerland:Computer Graphics and Society,2006:33-42.
[10]  Jenkins Odest Chadwicke,Mataric Maja J.Automated derivation of behavior vocabularies for autonomous humanoid motion[C] // Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems.New York,USA:ACM,2003:225-232.
[11]  Tenenbaum Joshua B,Silva Vin de,Langford John C.A global geometric framework for nonlinear dimensionality reduction[J].Science,290(5500):2319-2323.
[12]  Roweis Sam T,Saul Lawrence K.Nonlinear dimensionality reduction by locally linear embedding[J].Science,290 (5500):2323-2326.
[13]  Xiao Jun,Zhuang Yueting,Chen Cheng.Automatic synthesisand editing of motion styles[C]//Proceedings of the 3rd Conference on Intelligent CAD and Digital Entertainment,Ji\'nan:Shandong University.2006:249-256.[肖俊,庄越挺,陈成.风格化人体运动数据的自动生成与编辑[C]//第三届智能CAD与数字娱乐学术会议论文集.济南:山东大学出版社,2006:249-256.]
[14]  Allen Brett,Curless Brian,Popovi Zoran.Articulated body deformation from range scan data[C]//Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques.New York; ACM,2002:612-619.
[15]  Kovar Lucas,Gleicher Michael.Flexible automatic motion blending with registration curves[C]//Proceedings of the 2003 ACM SIGGRAPH/Eurographics,Aire-la-Ville,Switzerland:Eurographics Association,2003:214-224.
[16]  Zhao Liming,Safonova Alia.Achieving good connectivity in motion graphs[J].Graphical Models,2009,71(4):139-152.
[17]  Kovar Lucas,Gleicher Michael.Automated extraction and parameterization of motions in large data sets[J].ACM Transactions on Graphics(TOG),2004,23(3):559-568.
[18]  Elizabeth Seward A,Bodenheimer Bobby.Using nonlinear dimensionality reduction in 3D figure animation[C]// Proceedings of the 43rd Annual Southeast Regional Conference,New York,USA:ACM Press,2005:392-410.
[19]  Lee Chan-Su,Elgammal Ahmed.Human motion synthesis by motionmanifold learning and motion primitive segmentation[C] // Proceedings of Articulated Motion and Deformable Objects (AMDO),Heidelberg,Germany:Springer Berlin,2006; 464-473.
[20]  Shin Hyun Joon,Lee Jehee.Motion synthesis and editing in low-dimensional spaces[J].Computer Animation and Virtual Worlds,2006,17(3/4):219-227.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133