We propose a new dynamic model which can be used within blob trackers to track the target's center of gravity. A strong point of the model is that it is designed to track a va...
Matej Kristan, Stanislav Kovacic, Ales Leonardis, ...
Locally Orderless Tracking (LOT) is a visual tracking algorithm that automatically estimates the amount of local (dis)order in the object. This lets the tracker specialize in both...
Shaul Oron, Aharon Bar-Hillel, Dan Levi, Shai Avid...
Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densi...
In this paper, we present a robust text-independent speaker recognition system. The proposed system mainly includes an SNR-aware subspace-based enhancement technique and probabili...
We present a probabilistic approach to shape matching which is invariant to rotation, translation and scaling. Shapes are represented by unlabeled point sets, so discontinuous bou...