Real-time 2½D head pose recovery for model-based video-coding

Author

Cordea, M.D. ; Petriu, E.M. ; Georganas, N.D. ; Petriu, D.C. ; Whalen, T.E.

Author_Institution

Sch. of Inf. Technol. & Eng., Ottawa Univ., Ont., Canada

Volume

2

fYear

2000

fDate

2000

Firstpage

601

Abstract

This paper discusses a 2½D tracking method allowing real-time recovery of the 3D position and orientation of a head moving in its image plane. The described method uses a 2D elliptical head model, region- and edge-based matching algorithms, and a linear Kalman filter estimation. The resulting motion tracking system works in a realistic environment without makeup on the face, with uncalibrated camera and unknown lighting conditions and background

Keywords

Kalman filters; edge detection; image matching; optical tracking; real-time systems; video coding; 2D elliptical head model; edge-based matching algorithms; image plane; linear Kalman filter estimation; model-based video-coding; motion tracking system; real-time 2½D head pose recovery; region-based matching algorithms; tracking method; uncalibrated camera; unknown lighting conditions; Cameras; Face detection; Feature extraction; Head; Image motion analysis; Layout; Motion estimation; Optical filters; Optical sensors; Target tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 2000. IMTC 2000. Proceedings of the 17th IEEE

Conference_Location

Baltimore, MD

ISSN

1091-5281

Print_ISBN

0-7803-5890-2

Type

conf

DOI

10.1109/IMTC.2000.848808

Filename

848808