MPI-INF Logo
Publications

Server    domino.mpi-inf.mpg.de

Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop

Author, Editor
Author(s):
Andriluka, Mykhaylo
Roth, Stefan
Schiele, Bernt		dblp
dblp
dblp
Not MPG Author(s):
Roth, Stefan
Editor(s):
BibTeX cite key*:
andriluka10cvpr
Title, Booktitle
Title*:
Monocular 3D Pose Estimation and Tracking by Detection
Booktitle*:
2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Event, URLs
Conference URL::
http://cvl.umiacs.umd.edu/conferences/cvpr2010/
Downloading URL:
http://www.d2.mpi-inf.mpg.de/sites/default/files/people/andriluka/cvpr10andriluka.pdf
Event Address*:
San Francisco, USA
Language:
English
Event Date*
(no longer used):
Organization:
Event Start Date:
15 June 2010
Event End Date:
17 June 2010
Publisher
Name*:
IEEE
URL:
http://ieeexplore.ieee.org/
Address*:
Piscataway, NJ
Type:
Vol, No, Year, pp.
Series:
Volume:
Number:
Month:
June
Pages:
623-630
Year*:
2010
VG Wort Pages:
ISBN/ISSN:
978-1-4244-6984-0
Sequence Number:
DOI:
10.1109/CVPR.2010.5540156
Note, Abstract, ©
(LaTeX) Abstract:
Automatic recovery of 3D human pose from monocular image sequences is a challenging and important research topic with numerous applications. Although current methods are able to recover 3D pose for a single person in controlled environments, they are severely challenged by real-world scenarios, such as crowded street scenes. To address this problem, we propose a three-stage process building on a number of recent advances. The first stage obtains an initial estimate of the 2D articulation and viewpoint of the person from single frames. The second stage allows early data association across frames based on tracking-by-detection. These two stages successfully accumulate the available 2D image evidence into robust estimates of 2D limb positions over short image sequences (= tracklets). The third and final stage uses those tracklet-based estimates as robust image observations to reliably recover 3D pose. We demonstrate state-of-the-art performance on the HumanEva II benchmark, and also show the applicability of our approach to articulated 3D tracking in realistic street conditions.
Keywords:
2D articulation estimation, 2D image evidence, 2D limb position, 3D human pose, articulated 3D tracking, crowded street scene, data association, detection tracking, monocular 3D pose estimation, monocular image sequence, three-stage process building, tracking-by-detection, tracklet-based estimates, viewpoint estimation, image sequences, object detection, optical tracking, pose estimation
Download
Access Level:
Public

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



BibTeX Entry:

@INPROCEEDINGS{andriluka10cvpr,
AUTHOR = {Andriluka, Mykhaylo and Roth, Stefan and Schiele, Bernt},
 TITLE = {Monocular {3D} Pose Estimation and Tracking by Detection},
 BOOKTITLE = {2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 PUBLISHER = {IEEE},
 YEAR = {2010},
 PAGES = {623--630},
 ADDRESS = {San Francisco, USA},
 MONTH = {June},
 ISBN = {978-1-4244-6984-0},
 DOI = {10.1109/CVPR.2010.5540156},
}

Entry last modified by Anja Becker, 04/11/2011
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)
[Library]		Created
01/17/2011 13:24:24
Revisions
6.
5.
4.
3.
2.		Editor(s)
Anja Becker
Anja Becker
Anja Becker
Anja Becker
Anja Becker		Edit Dates
11.04.2011 10:37:00
19.01.2011 11:17:38
18.01.2011 14:17:25
18.01.2011 14:15:36
18.01.2011 13:50:49