Singularities in Articulated Object Tracking with 2-D and 3-D Models

Jim Rehg and Daniel D. Morris
October, 1997.


Download
  • Adobe portable document format (pdf) (547KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
Three dimensional kinematic models are widely-used in video-based figure tracking. We show that these models can suffer from singularities when motion is directed along the viewing axis of a single camera. The single camera case is important because it arises in many interesting applications, such as motion capture from movie footage.

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 demonstrate tracking through singularities using synthetic and real examples.

We demonstrate the application of our model to motion capture from movies. Fred Astaire is tracked in a clip from the film ``Shall We Dance''. Some simple video edits are presented. These results demonstrate the benefits of the SPM in tracking with a single source of video.


Notes
Associated Project(s): Articulated Motion Tracking

Text Reference
Jim Rehg and Daniel D. Morris, "Singularities in Articulated Object Tracking with 2-D and 3-D Models," October, 1997.

BibTeX Reference
@incollection{Rehg_1997_3155,
   author = "Jim Rehg and Daniel D. Morris",
   title = "Singularities in Articulated Object Tracking with 2-D and 3-D Models",
   booktitle = "",
   publisher = "tech. report CRL 97/8, Digital Equipment Corporation, Cambridge Research Lab",
   month = "October",
   year = "1997",
}