Paper published in a book (Scientific congresses and symposiums)
Leveraging orientation knowledge to enhance human pose estimation methods
Azrour, Samir; Pierard, Sébastien; Van Droogenbroeck, Marc
2016In Articulated Motion and Deformable Objects AMDO 2016
Peer reviewed
 

Files


Full Text
Azrour2016Leveraging.pdf
Author postprint (735.75 kB)
Download
Annexes
presentation.pdf
Publisher postprint (2.27 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Human pose estimation; orientation; depth camera; Machine learning; 3D
Abstract :
[en] Predicting accurately and in real-time 3D body joint positions from a depth image is the cornerstone for many safety, biomedical, and entertainment applications. Despite the high quality of the depth images, the accuracy of existing human pose estimation methods from single depth images remains insufficient for some applications. In order to enhance the accuracy, we suggest to leverage a rough orientation estimation to dynamically select a 3D joint position prediction model specialized for this orientation. This orientation estimation can be obtained in real-time either from the image itself, or from any other clue like tracking. We demonstrate the merits of this general principle on a pose estimation method similar to the one used with Kinect cameras. Our results show that the accuracy is improved by up to 45.1 %, with respect to a method using the same model for all orientations.
Research center :
Montefiore ; Telim
Disciplines :
Computer science
Author, co-author :
Azrour, Samir ;  Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Pierard, Sébastien ;  Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Van Droogenbroeck, Marc  ;  Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Language :
English
Title :
Leveraging orientation knowledge to enhance human pose estimation methods
Publication date :
July 2016
Event name :
Conference on Articulated Motion and Deformable Objects (AMDO 2016)
Event organizer :
Francisco José Perales and Josef Kittler
Event place :
Palma de Mallorca, Spain
Event date :
from 13-07-2016 to 15-07-2016
Audience :
International
Main work title :
Articulated Motion and Deformable Objects AMDO 2016
Publisher :
Springer
Collection name :
Lecture Notes in Computer Science; 9756
Pages :
81-87
Peer reviewed :
Peer reviewed
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Available on ORBi :
since 12 May 2016

Statistics


Number of views
146 (35 by ULiège)
Number of downloads
280 (12 by ULiège)

Scopus citations®
 
1
Scopus citations®
without self-citations
0
OpenCitations
 
1

Bibliography


Similar publications



Contact ORBi