Authors:
Ahmed Rekik
1
;
Achraf Ben-Hamadou
2
and
Walid Mahdi
1
Affiliations:
1
Sfax University and Multimedia InfoRmation systems and Advanced Computing Laboratory (MIRACL), Tunisia
;
2
Paris-Est University, LIGM (UMR CNRS) and Center for Visual Computing, France
Keyword(s):
3D Face Tracking, RGB-D Cameras, Visibility Constraint, Photo-consistency, Particle Filter.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Computer Vision, Visualization and Computer Graphics
;
Enterprise Information Systems
;
Human and Computer Interaction
;
Human-Computer Interaction
;
Motion, Tracking and Stereo Vision
;
Tracking and Visual Navigation
Abstract:
This paper presents a new method for 3D face pose tracking in color image and depth data acquired by RGB-D (i.e., color and depth) cameras (e.g., Microsoft Kinect, Canesta, etc.). The method is based on a particle filter formalism and its main contribution lies in the combination of depth and image data to face the poor signal-to-noise ratio of low quality RGB-D cameras. Moreover, we consider a visibility constraint to handle partial occlusions of the face. We demonstrate the accuracy and the robustness of our method by performing a set of experiments on the Biwi Kinect head pose database.