Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop


Show entries of:

this year (2019) | last year (2018) | two years ago (2017) | Notes URL

Action:

login to update

Options:




Library Locked Library locked




Author, Editor

Author(s):

Hasler, Nils
Rosenhahn, Bodo
Thormählen, Thorsten
Wand, Michael
Gall, Jürgen
Seidel, Hans-Peter

dblp
dblp
dblp
dblp
dblp
dblp



Editor(s):





BibTeX cite key*:

HasRosThoWanGalSei09Audio

Title, Booktitle

Title*:

Markerless Motion Capture with Unsynchronized Moving Cameras

Booktitle*:

2009 IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2009

Event, URLs

URL of the conference:

http://www.cvpr2009.org/

URL for downloading the paper:

http://dx.doi.org/10.1109/CVPRW.2009.5206859

Event Address*:

Miami, USA

Language:

English

Event Date*
(no longer used):


Organization:


Event Start Date:

20 June 2009

Event End Date:

25 June 2009

Publisher

Name*:

IEEE

URL:


Address*:

Piscataway, NJ

Type:


Vol, No, Year, pp.

Series:


Volume:


Number:


Month:

June

Pages:

224-231

Year*:

2009

VG Wort Pages:


ISBN/ISSN:

978-1-4244-3992-8

Sequence Number:


DOI:

10.1109/CVPRW.2009.5206859



Note, Abstract, ©


(LaTeX) Abstract:

In this work we present an approach for markerless motion capture (MoCap) of articulated objects, which are recorded with multiple unsynchronized moving cameras. Instead of using fixed (and expensive) hardware synchronized cameras, this approach allows
us to track people with off-the-shelf handheld video ca\-me\-ras. To prepare a sequence for motion capture, we first reconstruct
the static background and the position of each camera using Structure-from-Motion (SfM). Then the cameras
are registered to each other using the reconstructed static background geometry.
Camera synchronization is achieved via the audio streams recorded by the ca\-me\-ras in parallel. Finally, a markerless MoCap approach is applied to recover positions and joint configurations of subjects. Feature tracks and dense background geometry are further used to stabilize the MoCap. The ex\-pe\-ri\-ments show examples with highly challenging indoor and outdoor scenes.



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{HasRosThoWanGalSei09Audio,
AUTHOR = {Hasler, Nils and Rosenhahn, Bodo and Thorm{\"a}hlen, Thorsten and Wand, Michael and Gall, J{\"u}rgen and Seidel, Hans-Peter},
TITLE = {Markerless Motion Capture with Unsynchronized Moving Cameras},
BOOKTITLE = {2009 IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2009},
PUBLISHER = {IEEE},
YEAR = {2009},
PAGES = {224--231},
ADDRESS = {Miami, USA},
MONTH = {June},
ISBN = {978-1-4244-3992-8},
DOI = {10.1109/CVPRW.2009.5206859},
}


Entry last modified by Anja Becker, 03/17/2010
Show details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)
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
03/24/2009 02:55:35 PM
Revisions
4.
3.
2.
1.
0.
Editor(s)
Anja Becker
Anja Becker
Nils Hasler
Nils Hasler
Nils Hasler
Edit Dates
17.03.2010 15:28:01
17.03.2010 15:25:29
01/12/2010 10:29:16 AM
01/12/2010 10:28:59 AM
03/24/2009 02:55:35 PM
Show details for Attachment SectionAttachment Section
Hide details for Attachment SectionAttachment Section