Visual measurement cues for face tracking

Author

Pnevmatikakis, Aristodemos ; Stergiou, Andreas ; Petsatodis, Theodoros ; Katsarakis, Nikos

Author_Institution

Autonomic & Grid Comput. Group, Athens Inf. Technol., Peania, Greece

fYear

2013

fDate

1-3 July 2013

Firstpage

1

Lastpage

6

Abstract

Particle filters allow for visual trackers with nonlinear measurements. In this paper we consider three different non-linear visual measurement cues, based on object detection, foreground segmentation and colour matching. Novel ways to obtain robust measurement likelihoods under a unified representation scheme are discussed, followed by a likelihood combination scheme for fusion. The resulting single and multi-cue particle filter trackers are compared in the scope of face tracking.

Keywords

face recognition; image segmentation; object detection; particle filtering (numerical methods); colour matching; face tracking; foreground segmentation; nonlinear measurements; object detection; particle filters; robust measurement likelihoods; unified representation scheme; visual measurement cues; visual trackers; Adaptation models; Atmospheric measurements; Face; Histograms; Image color analysis; Particle measurements; Target tracking; Face tracking; Fusion; Likelihood function; Particle filters; Visual measurements;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing (DSP), 2013 18th International Conference on

Conference_Location

Fira

ISSN

1546-1874

Type

conf

DOI

10.1109/ICDSP.2013.6622722

Filename

6622722