Paper published in a book (Scientific congresses and symposiums)
Estimation of human orientation based on silhouettes and machine learning principles
Pierard, Sébastien; Van Droogenbroeck, Marc
2012In International conference on pattern recognition applications and methods (ICPRAM)
Peer reviewed
 

Files


Full Text
Pierard2012Estimation.pdf
Author postprint (2.19 MB)
Estimation of human orientation based on silhouettes and machine learning principles
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Human; Silhouette; Machine learning; Orientation; Regression
Abstract :
[en] Estimating the orientation of the observed person is a crucial task for home entertainment, man-machine interaction, intelligent vehicles, etc. This is possible but complex with a single camera because it only provides one side view. To decrease the sensitivity to color and texture, we use the silhouette to infer the orientation. Under these conditions, we show that the only intrinsic limitation is to confuse the orientation q with the supplementary angle (that is 180°-theta), and that the shape descriptor must distinguish between mirrored images. In this paper, the orientation estimation is expressed and solved in the terms of a regression problem and supervised learning. In our experiments, we have tested and compared 18 shape descriptors; the best one achieves a mean error of 5:24°. However, because of the intrinsic limitation mentioned above, the range of orientations is limited to 180°. Our method is easy to implement and outperforms existing techniques.
Research center :
INTELSIG
Disciplines :
Electrical & electronics engineering
Author, co-author :
Pierard, Sébastien ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Van Droogenbroeck, Marc  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Language :
English
Title :
Estimation of human orientation based on silhouettes and machine learning principles
Publication date :
February 2012
Event name :
International conference on pattern recognition applications and methods (ICPRAM)
Event place :
Vilamoura, Portugal
Event date :
02-2012
Audience :
International
Main work title :
International conference on pattern recognition applications and methods (ICPRAM)
Pages :
51-60 (in volume 2)
Peer reviewed :
Peer reviewed
Commentary :
See the MakeHuman wikipedia page: http://en.wikipedia.org/wiki/MakeHuman
Available on ORBi :
since 28 October 2011

Statistics


Number of views
362 (23 by ULiège)
Number of downloads
618 (10 by ULiège)

Scopus citations®
 
7
Scopus citations®
without self-citations
7

Bibliography


Similar publications



Contact ORBi