MPI-INF Logo
Publications

Server    domino.mpi-inf.mpg.de

Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop

Author, Editor
Author(s):
Gall, Jürgen
Rosenhahn, Bodo
Brox, Thomas
Seidel, Hans-Peter		dblp
dblp
dblp
dblp
Not MPG Author(s):
Brox, Thomas
Editor(s):
Bebis, George
Boyle, Richard
Parvin, Bahram
Koracin, Darko
Remagnino, Paolo
Nefian, Ara
Meenakshisundaram, Gopi
Pascucci, Valerio
Zara, Jiri
Molineros, Jose
Theisel, Holger
Malzbender, Tom		dblp
dblp
dblp
dblp
dblp
dblp
dblp
dblp
dblp
dblp
dblp
dblp
Not MPII Editor(s):
Bebis, George
Boyle, Richard
Parvin, Bahram
Koracin, Darko
Remagnino, Paolo
Nefian, Ara
Meenakshisundaram, Gopi
Pascucci, Valerio
Zara, Jiri
Molineros, Jose
Malzbender, Tom
BibTeX cite key*:
GallISVC2005
Title, Booktitle
Title*:
Learning for Multi-view 3D Tracking in the Context of Particle Filters
Booktitle*:
Advances in Visual Computing : Second International Symposium, ISVC 2006, Part II
Event, URLs
Conference URL::
Downloading URL:
http://www.springerlink.com/content/j8765h5576l7211m/fulltext.pdf
Event Address*:
Lake Tahoe, NV, USA
Language:
English
Event Date*
(no longer used):
Organization:
Event Start Date:
6 November 2006
Event End Date:
8 November 2006
Publisher
Name*:
Springer
URL:
Address*:
Berlin, Germany
Type:
Vol, No, Year, pp.
Series:
Lecture Notes in Computer Science
Volume:
4292
Number:
Month:
Pages:
59-69
Year*:
2006
VG Wort Pages:
ISBN/ISSN:
978-3-540-48626-8; 3-540-48626-7; ISSN: 0302-9743
Sequence Number:
DOI:
Note, Abstract, ©
(LaTeX) Abstract:

In this paper we present an approach to use prior knowledge in the particle filter framework for 3D tracking, i.e. estimating the state parameters such as joint angles of a 3D object. The probability of the object’s states, including correlations between the state parameters, is learned a priori from training samples. We introduce a framework that integrates this knowledge into the family of particle filters and particularly into the annealed particle filter scheme. Furthermore, we show that the annealed particle filter also works with a variational model for level set based image segmentation that does not rely on background subtraction and, hence, does not depend on a static background. In our experiments, we use a four camera set-up for tracking the lower part of a human body by a kinematic model with 18 degrees of freedom. We demonstrate the increased accuracy due to the prior knowledge and the robustness of our approach to image distortions. Finally, we compare the results of our multi-view tracking system quantitatively to the outcome of an industrial marker based tracking system.
URL for the Abstract:
http://www.springerlink.com/content/j8765h5576l7211m/?p=df4ce94bb17c4c3c9aef19c1d58f7c43&pi=0
Download
Access Level:
Public

Correlation
MPG Unit:
Max-Planck-Institut für Informatik
MPG Subunit:
Computer Graphics Group
Appearance:
MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{GallISVC2005,
AUTHOR = {Gall, J{\"u}rgen and Rosenhahn, Bodo and Brox, Thomas and Seidel, Hans-Peter},
 EDITOR = {Bebis, George and Boyle, Richard and Parvin, Bahram and Koracin, Darko and Remagnino, Paolo and Nefian, Ara and Meenakshisundaram, Gopi and Pascucci, Valerio and Zara, Jiri and Molineros, Jose and Theisel, Holger and Malzbender, Tom},
 TITLE = {Learning for Multi-view {3D} Tracking in the Context of Particle Filters},
 BOOKTITLE = {Advances in Visual Computing : Second International Symposium, ISVC 2006, Part II},
 PUBLISHER = {Springer},
 YEAR = {2006},
 VOLUME = {4292},
 PAGES = {59--69},
 SERIES = {Lecture Notes in Computer Science},
 ADDRESS = {Lake Tahoe, NV, USA},
 ISBN = {978-3-540-48626-8},
; ISBN = {3-540-48626-7},
; ISBN = {ISSN: 0302-9743},
}

Entry last modified by Christine Kiesel, 02/25/2007
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
Bodo Rosenhahn		Created
11/21/2006 15:44:20
Revisions
4.
3.
2.
1.
0.		Editor(s)
Christine Kiesel
Christine Kiesel
Conny Liegl
Bodo Rosenhahn
Bodo Rosenhahn		Edit Dates
25.02.2007 20:19:04
12.02.2007 14:42:54
01/10/2007 12:16:00 PM
11/21/2006 03:56:47 PM
11/21/2006 03:44:20 PM