Loading...
Please wait, while we are loading the content...
Similar Documents
Tunable kernels for tracking (2006)
| Content Provider | CiteSeerX |
|---|---|
| Author | Parameswaran, Vasu Ramesh, Visvanathan Zoghlami, Imad |
| Description | In Proc. IEEE Conf. CVPR-2006 We present a tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking. The classic formulation of the tracking problem using mean-shift iterations encodes spatial information very loosely (i.e. using radially symmetric kernels). A problem with such a formulation is that it becomes easy for the tracker to get confused with other objects having the same feature distribution but different spatial configurations of features. Subsequent approaches have addressed this issue but not to the degree of generality required for tracking specific classes of objects and motions (e.g. humans walking). In this paper, we formulate the tracking problem in a manner that encodes the spatial configuration of features along with their density and yet retains robustness to spatial deformations and feature density variations. The encoding of spatial configuration is done using a set of kernels whose parameters can be optimized for a given class of objects and motions, off-line. The formulation enables the use of meanshift iterations and runs in real-time. We demonstrate better tracking results on synthetic and real image sequences as compared to the original mean-shift tracker. 1. |
| File Format | |
| Language | English |
| Publisher Date | 2006-01-01 |
| Access Restriction | Open |
| Subject Keyword | Tracking Problem Specific Class Tunable Representation Feature Distribution Spatial Configuration Tunable Kernel Spatial Deformation Real Image Sequence Mean-shift Iteration Subsequent Approach Meanshift Iteration Symmetric Kernel Classic Formulation Spatial Information Original Mean-shift Tracker Different Spatial Configuration Feature Density Variation |
| Content Type | Text |
| Resource Type | Article |
