We present a novel algorithm (which we call "FragTrack") for tracking an object in a video sequence. The template object is represented by multiple image fragments or pa...
Abstract. Robust tracking of objects in video is a key challenge in computer vision with applications in automated surveillance, video indexing, human-computer-interaction, gesture...
Pankaj Kumar, Michael J. Brooks, Anton van den Hen...
We propose an online algorithm based on local sparse representation for robust object tracking. Local image patches of a target object are represented by their sparse codes with a...
Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image fea...
Leonid Taycher, John W. Fisher III, Trevor Darrell
This paper addresses online learning of reference object distribution in the context of two hybrid tracking schemes that combine the mean shift with local point feature correspond...