Head Pose Estimation Using Multi-scale Gaussian Derivatives

Varun Jain 1, * James L. Crowley 1
* Corresponding author
1 PRIMA - Perception, recognition and integration for observation of activity
Inria Grenoble - Rhône-Alpes, UJF - Université Joseph Fourier - Grenoble 1, INPG - Institut National Polytechnique de Grenoble , CNRS - Centre National de la Recherche Scientifique : UMR5217
Abstract : In this paper we approach the problem of head pose estimation by combining Multi-scale Gaussian Derivatives with Support Vector Machines. We evaluate the approach on the Pointing04 and CMU-PIE data sets and to estimate the pan and tilt of the head from facial images. We achieved a mean absolute error of 6.9 degrees for pan and 8.0 degrees for tilt on the Pointing04 data set.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-00839527
Contributor : Varun Jain <>
Submitted on : Friday, June 28, 2013 - 1:21:10 PM
Last modification on : Wednesday, April 11, 2018 - 1:54:26 AM
Long-term archiving on : Sunday, September 29, 2013 - 4:37:06 AM

File

79440319.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Varun Jain, James L. Crowley. Head Pose Estimation Using Multi-scale Gaussian Derivatives. 18th Scandinavian Conference on Image Analysis, Jun 2013, Espoo, Finland. ⟨10.1007/978-3-642-38886-6_31⟩. ⟨hal-00839527⟩

Share

Metrics

Record views

501

Files downloads

685