A Rao-Blackwellized Parts-Constellation Tracker

11 years 9 months ago
A Rao-Blackwellized Parts-Constellation Tracker
We present a method for efficiently tracking objects represented as constellations of parts by integrating out the shape of the model. Parts-based models have been successfully applied to object recognition and tracking. However, the high dimensionality of such models present an obstacle to traditional particle filtering approaches. We can efficiently use parts-based models in a particle filter by applying Rao-Blackwellization to integrate out continuous parameters such as shape. This allows us to maintain multiple hypotheses for the pose of an object without the need to sample in the high-dimensional spaces in which partsbased models live. We present experimental results for a challenging biological tracking task.
Grant Schindler, Frank Dellaert
Added 22 Aug 2010
Updated 22 Aug 2010
Type Conference
Year 2006
Where ECCV
Authors Grant Schindler, Frank Dellaert
Comments (0)