Home News About Us Contact Contributors Disclaimer Privacy Policy Help FAQ

Home
Search
Quick Search
Advanced
Fulltext
Browse
Collections
Persons
My eDoc
Session History
Login
Name:
Password:
Documentation
Help
Support Wiki
Direct access to
document ID:


          Institute: MPI für Informatik     Collection: Computer Vision and Multimodal Computing     Display Documents



ID: 536682.0, MPI für Informatik / Computer Vision and Multimodal Computing
Monocular 3D Pose Estimation and Tracking by Detection
Authors:Andriluka, Mykhaylo; Roth, Stefan; Schiele, Bernt
Language:English
Publisher:IEEE
Place of Publication:Piscataway, NJ
Date of Publication (YYYY-MM-DD):2010
Title of Proceedings:2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). - Pt. 1
Start Page:623
End Page:630
Place of Conference/Meeting:San Francisco, USA
(Start) Date of Conference/Meeting
 (YYYY-MM-DD):
2010-06-15
End Date of Conference/Meeting 
 (YYYY-MM-DD):
2010-06-17
Audience:Experts Only
Intended Educational Use:No
Abstract / Description: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.
Last Change of the Resource (YYYY-MM-DD):2011-01-19
External Publication Status:published
Document Type:Conference-Paper
Communicated by:Bernt Schiele
Affiliations:MPI für Informatik/Computer Vision and Multimodal Computing
Identifiers:LOCALID:C12576EE0048963A-205A6C785D49C581C125781B0044271E-...
URL:http://www.d2.mpi-inf.mpg.de/sites/default/files/p...
DOI:10.1109/CVPR.2010.5540156
ISBN:978-1-4244-6984-0
The scope and number of records on eDoc is subject to the collection policies defined by each institute - see "info" button in the collection browse view.