Abstract. We present a detection-based three-level hierarchical association approach to robustly track multiple objects in crowded environments from a single camera. At the low lev...
Tracking multiple interacting objects represents a challenging area in computer vision. The tracking problem in general can be formulated as the task of recovering the spatio-temp...
Abstract. This paper describes the implementation of a decentralized architecture for autonomous teams of aerial and ground vehicles engaged in active perception. We provide a theo...
Ben Grocholsky, Selcuk Bayraktar, Vijay Kumar, Cam...
In this paper we propose a new method that addresses the problem of tracking the bitmap (silhouette) of an object in a video under very general conditions. We assume a general tar...
We present in this paper a novel object tracking system based on 3D contour models. For this purpose, we integrate two complimentary likelihoods, defined on local color statistics...