A new exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especially temporal fusion, in a principled manner. Exemplars are selected representatives of raw training data, used here to represent probabilistic mixture distributions of object configurations. Their use avoids tedious hand-construction of object models and problems with changes of topology. Using exemplars in place of a parameterized model poses several challenges, addressed here with what we call the "Metric Mixture" (M/sup 2/) approach. The M/sup 2/ model has several valuable properties. Principally, it provides alternatives to standard learning algorithms by allowing the use of metrics that are not embedded in a vector space. Secondly, it uses a noise model that is learned from training data. Lastly, it eliminates any need for an assumption of probabilistic pixelwise independence. Experiments demonstrate the effectiveness of the M/sup 2/ model in two domains tracking walking people using chamfer distances on binary edge images and tracking mouth movements by means of a shuffle distance.
Probabilistic tracking in a metric space
2001-01-01
999131 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Probabilistic Tracking in a Metric Space
British Library Conference Proceedings | 2001
|Probabilistic Tracking with Exemplars in a Metric Space
British Library Online Contents | 2002
|NTRS | 2008
Dempster-Schafer Inspired Association Framework and Tracking Metric for Space Objects
British Library Conference Proceedings | 2020
|Developing a Probabilistic Metric of Midair Collision Risk
Online Contents | 1997
|