The template update problem

被引:540
作者
Matthews, I [1 ]
Ishikawa, T [1 ]
Baker, S [1 ]
机构
[1] Carnegie Mellon Univ, Inst Robot, Pittsburgh, PA 15232 USA
关键词
template tracking; the Lucas-Kanade algorithm; active appearance models;
D O I
10.1109/TPAMI.2004.16
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Template tracking dates back to the 1981 Lucas-Kanade algorithm. One question that has received very little attention, however, is how to update the template so that it remains a good model of the tracked object. We propose a template update algorithm that avoids the "drifting" inherent in the naive algorithm.
引用
收藏
页码:810 / 815
页数:6
相关论文
共 10 条
[1]  
[Anonymous], P EUR C COMP VIS ECC
[2]   Lucas-Kanade 20 years on: A unifying framework [J].
Baker, S ;
Matthews, I .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 56 (03) :221-255
[3]  
Baker S, 2001, PROC CVPR IEEE, P1090
[4]   EigenTracking: Robust matching and tracking of articulated objects using a view-based representation [J].
Black, MJ ;
Jepson, AD .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1998, 26 (01) :63-84
[5]   Active appearance models [J].
Cootes, TF ;
Edwards, GJ ;
Taylor, CJ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (06) :681-685
[6]   Efficient region tracking with parametric models of geometry and illumination [J].
Hager, GD ;
Belhumeur, PN .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1998, 20 (10) :1025-1039
[7]  
Lucas B. D., 1981, P INT JOINT C ART IN, P674, DOI DOI 10.5555/1623264.1623280
[8]   Active appearance models revisited [J].
Matthews, I ;
Baker, S .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) :135-164
[9]   A bootstrapping algorithm for learning linear models of object classes [J].
Vetter, T ;
Jones, MJ ;
Poggio, T .
1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :40-46
[10]   Robust full-motion recovery of head by dynamic templates and re-registration techniques [J].
Xiao, J ;
Kanade, T ;
Cohn, JF .
FIFTH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, PROCEEDINGS, 2002, :163-169