International Conference on Computer Analysis of Images and Patterns

CAIP 2015: Computer Analysis of Images and Patterns pp 254-265

Real-Time Head Pose Estimation Using Multi-variate RVM on Faces in the Wild

Conference paper

DOI: 10.1007/978-3-319-23117-4_22

Volume 9257 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Selim M., Pagani A., Stricker D. (2015) Real-Time Head Pose Estimation Using Multi-variate RVM on Faces in the Wild. In: Azzopardi G., Petkov N. (eds) Computer Analysis of Images and Patterns. CAIP 2015. Lecture Notes in Computer Science, vol 9257. Springer, Cham

Abstract

Various computer vision problems and applications rely on an accurate, fast head pose estimator. We model head pose estimation as a regression problem. We show that it is possible to use the appearance of the facial image as a feature which depicts the pose variations. We use a parametrized Multi-Variate Relevance Vector Machine (MVRVM) to learn the three rotation angles of the face (yaw, pitch, and roll). The input of the MVRVM is normalized mean pixel intensities of the face patches, and the output is the three head rotation angles. We evaluated our approach on the challenging YouTube faces dataset. We achieved a head pose estimation with an average error tolerance of \(\pm \)6.5\(^\circ \) in the yaw rotation angle, and less than \(\pm \)2.5\(^\circ \) in both the pitch and roll angles. The time taken in one prediction is 2-3 milliseconds, hence suitable for real-time applications.

Keywords

Head pose estimation Real-time MVRVM YouTube faces 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Augmented Vision Research Group, German Research Center for Artificial Intelligence (DFKI)Technical University of KaiserslauternKaiserslauternGermany