Tracking deformable motion

Author

Patras, I. ; Pantic, M.

Author_Institution

Electr. Eng., Math., & Comput. Sci., Delft Univ. of Technol.

Volume

2

fYear

2005

fDate

12-12 Oct. 2005

Firstpage

1066

Lastpage

1071

Abstract

This paper addresses the problem of template-based tracking of non rigid objects. We use the well-known framework of auxiliary particle filtering and propose an observation model that explicitly addresses appearance changes that are caused by local deformations of the tracked object. In addition, by adopting a colour difference that is invariant to local changes in the illumination, the proposed observation model can deal with changing lighting conditions and shadows. Experimental results with real image sequences demonstrate the efficiency of the proposed method in tracking facial features, such as mouth and eye corners

Keywords

feature extraction; image colour analysis; image motion analysis; image reconstruction; image sequences; lighting; object recognition; particle filtering (numerical methods); tracking; deformable motion tracking; facial feature tracking; image colour difference; image illumination; image lighting condition; image sequences; image shadowing; nonrigid object tracking; particle filtering; template-based tracking; tracked object deformation; Color; Computer science; Face detection; Filtering; Image databases; Image sequences; Lighting; Mathematics; Robustness; Target tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2005 IEEE International Conference on

Conference_Location

Waikoloa, HI

Print_ISBN

0-7803-9298-1

Type

conf

DOI

10.1109/ICSMC.2005.1571287

Filename

1571287