Hough-based Tracking of Non-Rigid Objects

10 years 5 months ago
Hough-based Tracking of Non-Rigid Objects
Online learning has shown to be successful in tracking of previously unknown objects. However, most approaches are limited to a bounding-box representation with fixed aspect ratio. Thus, they provide a less accurate foreground/background separation and cannot handle highly non-rigid and articulated objects. This, in turn, increases the amount of noise introduced during online self-training. In this paper, we present a novel tracking-by-detection approach to overcome this limitation based on the generalized Hough-transform. We extend the idea of Hough Forests to the online domain and couple the votingbased detection and back-projection with a rough segmentation based on GrabCut. This significantly reduces the amount of noisy training samples during online learning and thus effectively prevents the tracker from drifting. In the experiments, we demonstrate that our method successfully tracks a variety of previously unknown objects even under heavy non-rigid transformations, partial occ...
Martin Godec, Peter M. Roth, Horst Bischof
Added 11 Dec 2011
Updated 11 Dec 2011
Type Journal
Year 2011
Where ICCV
Authors Martin Godec, Peter M. Roth, Horst Bischof
Comments (0)