Online motion capture marker Labeling for multiple interacting articulated targets

被引:16
作者
Yu, Qian [1 ]
Li, Qing
Deng, Zhigang
机构
[1] Univ Houston, Dept Comp Sci, Comp Graph & Interact Media Lab, Houston, TX 77004 USA
[2] Univ So Calif, Inst Robot & Intelligent Syst, Los Angeles, CA 90089 USA
关键词
19;
D O I
10.1111/j.1467-8659.2007.01070.x
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In this paper, we propose an online motion capture marker labeling approach for multiple interacting articulated targets. Given hundreds of unlabeled motion capture markers,from multiple articulated targets that are interacting each other our approach automatically labels these markers frame by frame, by fitting rigid bodies and exploiting trained structure and motion models. Advantages of our approach include: 1) our method is an online algorithm, which requires no user interaction once the algorithm starts. 2) Our method is more robust than traditional the closest point-based approaches by automatically imposing the structure and motion models. 3) Due to the use of the structure model which encodes the rigidity of each articulated body of captured targets, our method can recover missing markers robustly. Our approach is efficient and particularly suited for online computer animation and video game applications.
引用
收藏
页码:477 / 483
页数:7
相关论文
共 19 条
[1]  
AGUIAR ED, 2006, P INT S VIS COMP ISV, P485
[2]  
Arikan O, 2002, ACM T GRAPHIC, V21, P483, DOI 10.1145/566570.566606
[3]  
Bregler C, 2002, ACM T GRAPHIC, V21, P399, DOI 10.1145/566570.566595
[4]  
Deng Z., 2006, P 2006 S INT 3D GRAP, P43, DOI DOI 10.1145/1111411.1111419]
[5]  
DENG Z, 2006, P ACM SIGGGRAPH EUR
[6]  
GLEICHER M., 1998, P 25 ANN C COMP GRAP, P33, DOI 10.1145/280814.280820
[7]  
Guerra-filho G.B., 2005, RITA, V12, P61
[8]  
HERDA L, 2000, CA 00 P COMP AN
[9]  
Hornung A, 2005, P IEEE VIRT REAL ANN, P75
[10]  
KIRK A, 2005, IEEE CVPR 2005