Reference : A two-step methodology for human pose estimation increasing the accuracy and reducing...
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/214238
A two-step methodology for human pose estimation increasing the accuracy and reducing the amount of learning samples dramatically
English
Azrour, Samir mailto [Université de Liège - ULiege > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Pierard, Sébastien [Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Geurts, Pierre [Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Van Droogenbroeck, Marc mailto [Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Sep-2017
Advanced Concepts for Intelligent Vision Systems
Yes
No
International
Advanced Concepts for Intelligent Vision Systems (ACIVS 2017)
from 18-09-2017 to 21-09-2017
Rudi Penne and Paul Scheunders
Antwerpen
Belgium
[en] Human pose estimation ; Orientation ; Machine learning
[en] In this paper, we present a two-step methodology to improve existing human pose estimation methods from a single depth image. Instead of learning the direct mapping from the depth image to the 3D pose, we first estimate the orientation of the standing person seen by the camera and then use this information to dynamically select a pose estimation model suited for this particular orientation. We evaluated our method on a public dataset of realistic depth images with precise ground truth joints location. Our experiments show that our method decreases the error of a state-of-the-art pose estimation method by 30%, or reduces the size of the needed learning set by a factor larger than 10.
Montefiore ; Telim
Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
Researchers ; Professionals
http://hdl.handle.net/2268/214238

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Azrour2017ATwoStep.pdfA two-step methodology for human pose estimation increasing the accuracy and reducing the amount of learning samples dramaticallyAuthor postprint395.17 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.