VideoMocap: Modeling Physically Realistic Human Motion from Monocular Video Sequences

被引：53
作者：
Wei, Xiaolin [1 ]
Chai, Jinxiang [1 ]
机构：
[1] Texas A&M Univ, College Stn, TX 77843 USA
来源：
ACM TRANSACTIONS ON GRAPHICS | 2010年 / 29卷 / 04期
基金：
美国国家科学基金会;
关键词：
Video-based motion capture; performance animation; physics-based animation; data-driven animation; interactive 3D visual tracking; vision for graphics;
D O I：
10.1145/1778765.1778779
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
This paper presents a video-based motion modeling technique for capturing physically realistic human motion from monocular video sequences. We formulate the video-based motion modeling process in an image-based keyframe animation framework. The system first computes camera parameters, human skeletal size, and a small number of 3D key poses from video and then uses 2D image measurements at intermediate frames to automatically calculate the "in between" poses. During reconstruction, we leverage Newtonian physics, contact constraints, and 2D image measurements to simultaneously reconstruct full-body poses, joint torques, and contact forces. We have demonstrated the power and effectiveness of our system by generating a wide variety of physically realistic human actions from uncalibrated monocular video sequences such as sports video footage.
引用
收藏
页数：10
相关论文
共 33 条
[11]  
Elgammal A, 2004, PROC CVPR IEEE, P681
[12]  
Howe NR, 2000, ADV NEUR IN, V12, P820
[13]  
Huber P., 2011, ROBUST STAT
[14]  
Law J., 1986, Robust Statistics: The approach based on influence functions, V35
[15]   Learning physics-based motion style with nonlinear inverse optimization [J].
Liu, CK ;
Hertzmann, A ;
Popovic, Z .
ACM TRANSACTIONS ON GRAPHICS, 2005, 24 (03) :1071-1081
[16]  
Lourakis M.I.A., 2009, LEVMAR LEVENBERG MAR
[17]  
Loy G, 2004, LECT NOTES COMPUT SC, V2034, P442
[18]  
PAVLOVIC V., 2000, NIPS, V13, P981
[19]  
POLLARD NS, 2001, YAL WORKSH AD LEARN
[20]  
Popovic Z, 1999, COMP GRAPH, P11, DOI 10.1145/311535.311536
1234