Multi-view Based Estimation of Human Upper-Body Orientation

The knowledge about the body orientation of humans can improve speed and performance of many service components of a smart-room. Since many of such components run in parallel, an estimator to acquire this knowledge needs a very low computational complexity. In this paper we address these two points...

Full description

Saved in:
Bibliographic Details
Published in2010 20th International Conference on Pattern Recognition pp. 1558 - 1561
Main Authors Rybok, Lukas, Voit, Michael, Ekenel, Hazim Kemal, Stiefelhagen, Rainer
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2010
Subjects
bag-offeatures
body-orientation
Cameras
Context
Estimation
Feature extraction
Histograms
Humans
multi-view fusion
Shape
Online AccessGet full text

Cover

More Information
Summary:The knowledge about the body orientation of humans can improve speed and performance of many service components of a smart-room. Since many of such components run in parallel, an estimator to acquire this knowledge needs a very low computational complexity. In this paper we address these two points with a fast and efficient algorithm using the smart-room's multiple camera output. The estimation is based on silhouette information only and is performed for each camera view separately. The single view results are fused within a Bayesian filter framework. We evaluate our system on a subset of videos from the CLEAR 2007 dataset and achieve an average correct classification rate of 87.8%, while the estimation itself just takes 12 ms when four cameras are used.
ISBN:1424475422
9781424475421
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2010.385