Paper published in a book (Scientific congresses and symposiums)
A two-step methodology for human pose estimation increasing the accuracy and reducing the amount of learning samples dramatically
Azrour, Samir; Pierard, Sébastien; Geurts, Pierre et al.
2017In Advanced Concepts for Intelligent Vision Systems
Peer reviewed
 

Files


Full Text
Azrour2017ATwoStep.pdf
Author postprint (404.66 kB)
A two-step methodology for human pose estimation increasing the accuracy and reducing the amount of learning samples dramatically
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Human pose estimation; Orientation; Machine learning
Abstract :
[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.
Research center :
Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège
Telim
Disciplines :
Computer science
Author, co-author :
Azrour, Samir ;  Université de Liège - ULiège > 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  ;  Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Language :
English
Title :
A two-step methodology for human pose estimation increasing the accuracy and reducing the amount of learning samples dramatically
Publication date :
September 2017
Event name :
Advanced Concepts for Intelligent Vision Systems (ACIVS 2017)
Event organizer :
Rudi Penne and Paul Scheunders
Event place :
Antwerpen, Belgium
Event date :
from 18-09-2017 to 21-09-2017
Audience :
International
Main work title :
Advanced Concepts for Intelligent Vision Systems
Publisher :
Springer
Collection name :
Lecture Notes in Computer Science, volume 10617
Pages :
3-14
Peer reviewed :
Peer reviewed
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Available on ORBi :
since 13 September 2017

Statistics


Number of views
175 (15 by ULiège)
Number of downloads
313 (13 by ULiège)

Scopus citations®
 
2
Scopus citations®
without self-citations
2
OpenCitations
 
2

Bibliography


Similar publications



Contact ORBi