This paper appears in: Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on
Publication Date: 23-25 Jun 1998
On page(s): 289-296
Meeting Date: 06/23/1998 - 06/25/1998
Location: Santa Barbara, CA, USA
ISSN: 1063-6919
ISBN: 0-8186-8497-6
References Cited: 18
INSPEC Accession Number: 5985858
Digital Object Identifier: 10.1109/CVPR.1998.698622
Current Version Published: 2002-08-06
Abstract
We analyze the use of kinematic constraints for articulated object
tracking. Conditions for the occurrence of singularities in 3-D models
are presented and their effects on tracking are characterized We
describe a novel 2-D Scaled Prismatic Model (SPM) for figure
registration. In contrast to 3-D kinematic models, the SPM has fewer
singularity problems and does not require detailed knowledge of the 3-D
kinematics. We fully characterize the singularities in the SPM and
illustrate tracking through singularities using synthetic and real
examples with 3-D and 2-D models. Our results demonstrate the
significant benefits of the SPM in tracking with a single source of
video
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
