Skip to Main content Skip to Navigation
New interface
Conference papers

Switching Linear Inverse-Regression Model for Tracking Head Pose

Vincent Drouard 1 Sileye Ba 1 Radu Horaud 1 
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, LJK - Laboratoire Jean Kuntzmann
Abstract : We propose to estimate the head-pose angles (pitch, yaw, and roll) by simultaneously predicting the pose parameters from observed high-dimensional feature vectors, and tracking these parameters over time. This is achieved by embedding a Gaussian mixture of linear inverse-regression model into a dynamic Bayesian model. The use of a switching Kalman filter (SKF) enables a principled way of carrying out this embedding. The SKF governs the temporal predic-tive distribution of the pose parameters (modeled as continuous latent variables) conditioned by the discrete variables associated with the mixture of linear inverse-regression formulation. We formally derive the equations of the proposed switching linear regression model, we propose an approximation that is both identifiable and computation-ally tractable, we design an EM procedure to estimate the SKF parameters in closed-form, and we carry out experiments and comparisons with other methods using recently released datasets.
Document type :
Conference papers
Complete list of metadata

Cited literature [40 references]  Display  Hide  Download
Contributor : Perception team Connect in order to contact the contributor
Submitted on : Tuesday, January 10, 2017 - 10:58:02 AM
Last modification on : Wednesday, May 4, 2022 - 12:12:05 PM
Long-term archiving on: : Tuesday, April 11, 2017 - 2:04:15 PM


Files produced by the author(s)




Vincent Drouard, Sileye Ba, Radu Horaud. Switching Linear Inverse-Regression Model for Tracking Head Pose. IEEE Winter Conference on Applications of Computer Vision, Mar 2017, Santa Rosa, CA, United States. pp.1232-1240, ⟨10.1109/WACV.2017.142⟩. ⟨hal-01430727⟩



Record views


Files downloads