We present a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. We develop an online feature selection mechanism based on the two-class variance ratio measure, applied to log likelihood distributions computed with respect to a given feature from samples of object and background pixels. This feature selection mechanism is embedded in a tracking system that adaptively selects the top-ranked discriminative features for tracking. Examples are presented to illustrate how the method adapts to changing appearances of both tracked object and scene background.
On-line selection of discriminative tracking features
2003-01-01
601000 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
On-Line Selection of Discriminative Tracking Features
British Library Conference Proceedings | 2003
|Online selection of discriminative pixel-pair feature for tracking
Tema Archiv | 2010
|Discriminative Mean Shift Tracking with Auxiliary Particles
Springer Verlag | 2007
|Multi-object tracking via discriminative appearance modeling
British Library Online Contents | 2016
|