Kernel-Based Object Tracking

DMCA

Kernel-Based Object Tracking (2003)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Dorin Comaniciu , Visvanathan Ramesh , Peter Meer

Citations:

885 - 4 self

BibTeX

@MISC{Comaniciu03kernel-basedobject,
    author = {Dorin Comaniciu and Visvanathan Ramesh and Peter Meer},
    title = {Kernel-Based Object Tracking},
    year = {2003}
}

OpenURL

Abstract

A new approach toward target representation and localization, the central component in visual tracking of non-rigid objects, is proposed. The feature histogram based target representations are regularized by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples the new method successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data association techniques is also discussed. We describe only few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking. Keywords: non-rigid object tracking; target localization and representation; spatially-smooth similarity function; Bhattacharyya coefficient; face tracking. 1

Keyphrases

kernel-based object tracking target representation bhattacharyya coefficient spatially-smooth similarity function new method new approach presented tracking face tracking scale variation camera motion local maximum mean shift procedure motion model spatial masking feature histogram non-rigid object tracking isotropic kernel motion filter partial occlusion gradient-based optimization data association technique target localization problem similarity measure background information visual tracking non-rigid object central component potential application

DMCA