- Abstract:
- 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^2) approach, which has a number of attractions. 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^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.
- Links To Paper
- No links available
- Bibtex format
- @Article{EDI-INF-RR-1093,
- author = {
K Toyama
and Andrew Blake
},
- title = {Probabilistic Tracking with Exemplars in a Metric Space},
- journal = {International Journal of Computer Vision},
- publisher = {Springer},
- year = 2002,
- volume = {48 (1)},
- pages = {9-19},
- doi = {10.1023/A:1014899027014},
- }
|