Title :
The template update problem
Author :
Matthews, Iain ; Ishikawa, Takahiro ; Baker, Simon
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
fDate :
6/1/2004 12:00:00 AM
Abstract :
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.
Keywords :
computer vision; optimisation; Lucas-Kanade algorithm; template tracking; template update problem; Active appearance model; Computer vision; Error correction; Heuristic algorithms; Image converters; Pixel; Region 5; Tracking; Video sequences; Template tracking; active appearance models.; the Lucas-Kanade algorithm; Algorithms; Artificial Intelligence; Image Enhancement; Image Interpretation, Computer-Assisted; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Video Recording;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2004.16
