We present a Dynamic Data Driven Application System (DDDAS) to track 2D shapes across large pose variations by learning non-linear shape manifold as overlapping, piecewise linear s...
We present a novel method for the discovery and statistical representation of motion patterns in a scene observed by a static camera. Related methods involving learning of pattern...
We propose a technique for text document tracking over a large range of viewpoints. Since the popular SIFT or SURF descriptors typically fail on such documents, our method conside...
Abstract—Learning dynamical systems is one of the important problems in many fields. In this paper, we present an algorithm for learning non-linear dynamical systems which works...
Abstract— We address the problem of vision-based multiperson tracking in busy pedestrian zones using a stereo rig mounted on a mobile platform. Specifically, we are interested i...
Andreas Ess, Bastian Leibe, Konrad Schindler, Luc ...