19 search results - page 4 / 4 » Visual Tracking by Adaptive Kalman Filtering and Mean Shift |
NIPS
2004
13 years 6 months ago
2004
Most existing tracking algorithms construct a representation of a target object prior to the tracking task starts, and utilize invariant features to handle appearance variation of...
CVPR
2008
IEEE
14 years 7 months ago
2008
IEEE
Recently, a novel Log-Euclidean Riemannian metric [28] is proposed for statistics on symmetric positive definite (SPD) matrices. Under this metric, distances and Riemannian means ...
ICCV
2007
IEEE
14 years 7 months ago
2007
IEEE
Most existing subspace analysis-based tracking algorithms utilize a flattened vector to represent a target, resulting in a high dimensional data learning problem. Recently, subspa...
CVPR
2008
IEEE
14 years 7 months ago
2008
IEEE
Given an object model and a black-box measure of similarity between the model and candidate targets, we consider visual object tracking as a numerical optimization problem. During...