Estimation of human orientation in images captured with a range camera

Authors:
Sébastien Piérard;Damien Leroy;Jean-Frédéric Hansen;Marc Van Droogenbroeck
Affiliations:
INTELSIG Laboratory, Montefiore Institute, University of Liège, Belgium;INTELSIG Laboratory, Montefiore Institute, University of Liège, Belgium;INTELSIG Laboratory, Montefiore Institute, University of Liège, Belgium;INTELSIG Laboratory, Montefiore Institute, University of Liège, Belgium
Venue:
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
Year:
2011

Citing 8
Cited 0

Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recovering 3D Human Pose from Monocular Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Extremely randomized trees

Machine Learning
Body Part Detection for Human Pose Estimation and Tracking

WMVC '07 Proceedings of the IEEE Workshop on Motion and Video Computing
Ideas and methods for modeling 3D human figures: the principal algorithms used by MakeHuman and their implementation in a new approach to parametric modeling

COMPUTE '08 Proceedings of the 1st Bangalore Annual Compute Conference
An intelligent fitting room using multi-camera perception

Proceedings of the 13th international conference on Intelligent user interfaces
A 3D Shape Descriptor for Human Pose Recovery

AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects
Multi-view Based Estimation of Human Upper-Body Orientation

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Estimating the orientation of the observed person is a crucial task for some application fields like home entertainment, man-machine interaction, or intelligent vehicles. In this paper, we discuss the usefulness of conventional cameras for estimating the orientation, present some limitations, and show that 3D information improves the estimation performance. Technically, the orientation estimation is solved in the terms of a regression problem and supervised learning. This approach, combined to a slicing method of the 3D volume, provides mean errors as low as 9.2° or 4.3° depending on the set of considered poses. These results are consistent with those reported in the literature. However, our technique is faster and easier to implement than existing ones.