A system for real-time synthesis of subtle expressivity for life-life MPEG-4 based virtual characters

被引:0
|
作者
Bonamico, C [1 ]
Braccini, C [1 ]
Lavagetto, F [1 ]
Costa, M [1 ]
机构
[1] Univ Genoa, DIST, Genoa, Italy
关键词
multimodal interfaces; 3D animation; facial animation; MPEG-4; embodied conversational agents; virtual characters; believability; subtle expressiveness;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Non-verbal behaviors have a key role in making a Virtual Character appear life-like. We describe an extensible system for the specification, control and real-time generation of facial expressions and gestures. The system approximates in a MPEG-4 based Virtual Character the wide expressive range, dynamism (an expression's meaning significantly depends on its temporal evolution) and variability. (an emotion is never expressed exactly in the same way by different people, and even by the same person at different times), typical of human nonverbal behavior. The MPEG-4 standard only allows high-level control of 6 basic emotions, and does not explicitly support the description of an expression temporal evolution. Our approach has been that of creating a hierarchical model of expressiveness; expressions are defined in term of parameterized functions controlling low-level animation parameters trajectories (by means of an XML-based Expression Definition Markup Language). The real-time generation of those expressions is performed by an Expression Synthesis Engine. The system allows to effectively modulate expressivity both at design-time (the developer tweaks the parameters to give the character a given expressive style), and at run-time (the engine automatically changes the way in which an expression is performed each time), producing controllable, but non-deterministic, behavior patterns, a key factor for enhancing believability.
引用
收藏
页码:55 / 58
页数:4
相关论文
共 50 条
  • [41] Real time facial expression recognition system with applications to facial animation in MPEG-4
    Chandrasiri, Naiwala Pathirannehelage
    Naemura, Takeshi
    Harashima, Hiroshi
    IEICE Transactions on Information and Systems, 2001, E84-D (08) : 1007 - 1017
  • [42] Real time facial expression recognition system with applications to facial animation in MPEG-4
    Chandrasiri, NP
    Naemura, T
    Harashima, H
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2001, E84D (08): : 1007 - 1017
  • [43] Determination of the acceptable MPEG-4 quality for clinical real-time tele-echocardiography services
    Giordano, Andrea
    Comazzi, Fabio
    Scapellato, Francesco
    Eleuteri, Ermanno
    Giannuzzi, Pantaleo
    Minuco, Giuseppe
    ANNALI DELL ISTITUTO SUPERIORE DI SANITA, 2009, 45 (04): : 372 - 377
  • [44] An efficient motion estimation algorithm for real-time MPEG-4 video encoding on multimedia processors
    Ma, SY
    Shen, CF
    Chen, LG
    PROCEEDINGS OF WORKSHOP AND EXHIBITION ON MPEG-4, 2002, : 67 - 70
  • [45] Efficient real-time implementation of MPEG-4 audiovisual decoder using DSP and RISC chips
    Choi, BD
    Choi, KS
    Ko, SJ
    Morales, AW
    ICCE: 2003 INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, DIGEST OF TECHNICAL PAPERS, 2003, : 246 - 247
  • [46] An MPEG-4 based talking head for real time voice chatting on Android platform
    Ozsvath, Jonathan
    Eros, Bence
    Toth, Akos
    Kunkli, Roland
    2017 8TH IEEE INTERNATIONAL CONFERENCE ON COGNITIVE INFOCOMMUNICATIONS (COGINFOCOM), 2017, : 369 - 370
  • [47] A high parallel-pipelined real-time motion estimation architecture for MPEG-4 simple profile - Optimized motion estimation architecture for MPEG-4 Part 9
    Lou, DJ
    Xu, NY
    Lin, XK
    2004 JOINT CONFERENCE OF THE 10TH ASIA-PACIFIC CONFERENCE ON COMMUNICATIONS AND THE 5TH INTERNATIONAL SYMPOSIUM ON MULTI-DIMENSIONAL MOBILE COMMUNICATIONS, VOLS 1 AND 2, PROCEEDINGS, 2004, : 691 - 695
  • [48] Distortion management of real-time MPEG-4 FGS video over downlink multicode (CDMA) networks
    Su, GM
    Han, Z
    Kwasinski, A
    Wu, M
    Liu, KJR
    Farvardin, N
    2004 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, VOLS 1-7, 2004, : 3071 - 3075
  • [49] Customizable MPEG-4 face player using real-time 2D image sequence
    Shin, MC
    Goldgof, D
    Kim, C
    Zhong, JL
    Guo, DB
    FIFTH IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION, PROCEEDINGS, 2000, : 91 - 97
  • [50] Dynamic GOP structure determination for real-time MPEG-4 advanced simple profile video encoder
    Wang, YL
    Wang, JX
    Lai, YW
    Su, AWY
    2005 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), VOLS 1 AND 2, 2005, : 293 - 296