Tracking persons in monocular image sequences

被引：128

作者：

Wachter, S

Nagel, HH

机构：

[1] Fraunhofer Inst Informat & Data Proc, D-76131 Karlsruhe, Germany

[2] Univ Karlsruhe, Fak Informat, Inst Algorithmen & Kognit Syst, D-76128 Karlsruhe, Germany

来源：

COMPUTER VISION AND IMAGE UNDERSTANDING | 1999年 / 74卷 / 03期

关键词：

modeling of persons; articulated motion estimation; Kalman filter;

D O I：

10.1006/cviu.1999.0758

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Quantitative geometric descriptions of the movements of persons are obtained by fitting the projection of a three-dimensional person model to consecutive frames of an image sequence. The kinematic of the person model is given by a homogeneous transformation tree and its body parts are modeled by right-elliptical cones. The values of a varying number of degrees of freedom (DOFs; body joints, position, and orientation of the person relative to the camera) can be determined according to the application and the kind of image sequence. The determination of the DOFs is understood as an estimation problem which is solved by an iterated extended Kalman filter (IEKF). For this purpose, the person model is augmented by a simple motion model of constant velocity for all DOFs which is used in the prediction step of the IEKF. In the update step, both region and edge information are used. Various experiments demonstrate the efficiency of our approach. (C) 1999 Academic Press.

引用

页码：174 / 192

页数：19

共 33 条

[1] Human motion analysis: A review
Aggarwal, JK
Cai, Q
[J]. IEEE NONRIGID AND ARTICULATED MOTION WORKSHOP, PROCEEDINGS, 1997, : 90 - 102
[2] [Anonymous], 1974, APPL OPTIMAL ESTIMAT
[3] [Anonymous], SIMULATING HUMANS
[4] Bar-Shalom Yaakov., 1993, ESTIMATION TRACKING
[5] Generating spatiotemporal models from examples
Baumberg, A
Hogg, D
[J]. IMAGE AND VISION COMPUTING, 1996, 14 (08) : 525 - 532
[6] Baumberg A. M., 1994, Proceedings of the 1994 IEEE Workshop on Motion of Non-Rigid and Articulated Objects (Cat. No.94TH0671-8), P194, DOI 10.1109/MNRAO.1994.346236
[7] Chang I.-C., 1996, Proceedings of the 13th International Conference on Pattern Recognition, P436, DOI 10.1109/ICPR.1996.546985
[8] KNOWLEDGE-GUIDED VISUAL-PERCEPTION OF 3-D HUMAN GAIT FROM A SINGLE IMAGE SEQUENCE
CHEN, Z
LEE, HJ
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1992, 22 (02): : 336 - 342
[9] Fu K. s., 1987, Robotics: Control, Sensing, Vision
[10] 3-D model-based tracking of humans in action: A multi-view approach
Gavrila, DM
Davis, LS
[J]. 1996 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1996, : 73 - 80

← 1 2 3 4 →