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.-A new approach toward target representation and localization, the central component in visual trackingof non-rigid objects, is proposed. The feature histogram based target representations are regularizedby spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functionssuitable for gradient-based optimization, hence, the target localization problem can be formulated usingthe basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyyacoefficient as similarity measure, and use the mean shift procedure to perform the optimization. In thepresented 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 alsodiscussed. We describe only few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking .