Kernel-based object tracking
Top Cited Papers
- 29 April 2003
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 25 (5) , 564-577
- https://doi.org/10.1109/tpami.2003.1195991
Abstract
A new approach toward target representation and localization, the central component in visual tracking of nonrigid 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 a few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking.Keywords
This publication has 63 references indexed in Scilit:
- Support Vector TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Elliptical head tracking using intensity gradients and color histogramsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Region tracking through image sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Adaptive Bayesian recognition in tracking rigid objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian trackingIEEE Transactions on Signal Processing, 2002
- View-Invariant Representation and Recognition of ActionsInternational Journal of Computer Vision, 2002
- Probabilistic data association methods for tracking complex visual objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Probabilistic Detection and Tracking of Motion BoundariesInternational Journal of Computer Vision, 2000
- An efficient implementation of Reid's multiple hypothesis tracking algorithm and its evaluation for the purpose of visual trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- An algorithm for tracking multiple targetsIEEE Transactions on Automatic Control, 1979