DocumentCode :
2355707
Title :
Model-based face tracking for dense motion field estimation
Author :
Gee, Timothy F. ; Mersereau, Russell M.
Author_Institution :
Image Sci. & Machine Vision Group, Oak Ridge Nat. Lab., TN, USA
fYear :
2001
fDate :
1-12 Oct 2001
Firstpage :
149
Lastpage :
153
Abstract :
When estimating the dense motion field of a video sequence, if little is known or assumed about the content, a limited constraint approach such as optical flow must be used. Since optical flow algorithms generally use a small spatial area in the determination of each motion vector the resulting motion field can be noisy, particularly if the input video sequence is noisy. If the moving subject is known to be a face, then we may use that constraint to improve the motion field results. This paper describes a method for deriving dense motion field data using a face tracking approach. A face model is manually initialized to fit a face at the beginning of the input sequence. Then a Kalman filtering approach is used to track the face movements and successively fit the face model to the face in each frame. The 2D displacement vectors are calculated from the projection of the facial model, which is allowed to move in 3D space and may have a 3D shape. We have experimented with planar, cylindrical, and Candide face models. The resulting motion field is used in multiple frame restoration of a face in noisy video
Keywords :
Kalman filters; face recognition; image sequences; motion estimation; Kalman filtering approach; dense motion field estimation; face model; face tracking; model-based face tracking; optical flow; video sequence; Filtering; Image motion analysis; Kalman filters; Motion estimation; Multi-stage noise shaping; Optical filters; Optical noise; Shape; Tracking; Video sequences;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Applied Imagery Pattern Recognition Workshop, AIPR 2001 30th
Conference_Location :
Washington, DC
Print_ISBN :
0-7695-1245-3
Type :
conf
DOI :
10.1109/AIPR.2001.991218
Filename :
991218
Link To Document :
بازگشت