Sciweavers

DAGM
2008
Springer

Efficient Tracking as Linear Program on Weak Binary Classifiers

13 years 5 months ago
Efficient Tracking as Linear Program on Weak Binary Classifiers
This paper demonstrates how a simple, yet effective, set of features enables to integrate ensemble classifiers in optical flow based tracking. In particular, gray value differences of pixel pairs are used for generating binary weak classifiers, forming the respective object representation. For the tracking step an affine motion model is proposed. By using hinge loss functions, the motion estimation problem can be formulated as a linear program. Experiments demonstrate robustness of the proposed approach and include comparisons to conventional tracking methods.
Michael Grabner, Christopher Zach, Horst Bischof
Added 19 Oct 2010
Updated 19 Oct 2010
Type Conference
Year 2008
Where DAGM
Authors Michael Grabner, Christopher Zach, Horst Bischof
Comments (0)