In example-based pose estimation, the configuration or "pose" of an evolving object is sought given visual evidence, having to rely uniquely on a
set of examples. We assume here that, in a training stage, a number of feature measurements is extracted from the available images,
while an "oracle" provides us with the true object pose at each instant.
In this scenario, a sensible approach consists in learning maps
from features to poses, using the information provided by the training set. In particular, multi-valued mappings linking feature values to set
of training poses can be easily constructed. A probability measure on any feature space is then naturally mapped to a convex set of probabilities
on the set of training poses, in a form of a "belief function". Given a test image, its feature measurements translate into a collection of belief
functions on the set of training poses, which when combined yield there an entire family of probability distributions. From the latter, both a single,
central pose estimate and a set of extremal estimates can be computed, together with a measure of how reliable the estimate is. Measuring the
conflict among the inferred belief functions provides a way of tackling occlusions and imperfect localization, and flags the need to update the
We call this technique "Belief Modelling Regression".
|Fabio Cuzzolin and Ruggero Frezza |
Evidential modeling for pose estimation
Proceedings of the 4th International Symposium on Imprecise Probabilities and Their Applications (ISIPTA'05)
Carnegie Mellon University, Pittsburgh, July 2005