Model-based estimation of 3D human motion

被引：86
作者：
Kakadiaris, I [1 ]
Metaxas, D
机构：
[1] Univ Houston, Dept Comp Sci, Houston, TX 77204 USA
[2] Univ Penn, Dept Comp & Informat Sci, Philadelphia, PA 19104 USA
来源：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2000年 / 22卷 / 12期
关键词：
motion estimation; human motion estimation; deformable models; model-based tracking; physics-based modeling;
D O I：
10.1109/34.895978
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents the formulations and techniques that we have developed for the three-dimensional, model-based, motion estimation of human movement from multiple cameras. Our method is based on the spatio-temporal analysis of the subject's silhouette and it has the advantage that the subject does not have to wear markers or other devices. We present tracking results from experiments involving the recovery of complex motions in the presence of significant occlusion.
引用
收藏
页码：1453 / 1459
页数：7
相关论文
共 34 条
[1]   Human motion analysis: A review [J].
Aggarwal, JK ;
Cai, Q .
IEEE NONRIGID AND ARTICULATED MOTION WORKSHOP, PROCEEDINGS, 1997, :90-102
[2]  
AZARBAYEJANI A, 1996, P IMAGE COM 96 MAY
[3]  
Barron C, 2000, PROC CVPR IEEE, P669, DOI 10.1109/CVPR.2000.855884
[4]   Tracking people with twists and exponential maps [J].
Bregler, C ;
Malik, J .
1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1998, :8-15
[5]  
CHAM TJ, 1999, P COMP VIS PATT REC, V2, P239
[6]  
Delamarre Q., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P716, DOI 10.1109/ICCV.1999.790292
[7]  
Deutscher J, 2000, PROC CVPR IEEE, P126, DOI 10.1109/CVPR.2000.854758
[8]  
Douros I., 1999, Proceedings IEEE International Workshop on Modelling People. MPeople'99, P29, DOI 10.1109/PEOPLE.1999.798343
[9]  
FELDMAR J, 1995, FIFTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, PROCEEDINGS, P549, DOI 10.1109/ICCV.1995.466891
[10]  
FREY W, 1996, NPSCS96003 COMP SCI
1234