Expanding Irregular Graph Pyramid for an Approaching Object
Luis A. Mateos18
, Dan Shao18
and Walter G. Kropatsch18 
| (18) |
Pattern Recognition and Image Processing Group, Vienna University of Technology, Favoritenstr. 9/1832, A-1040 Vienna, AUSTRIA |
Abstract
This paper focus on one of the major problems in model-based object tracking, the problem of how to dynamically update the
model to adapt changes in the structure and appearance of the target object. We adopt Irregular Graph Pyramids to hierarchically
represent the topological structure of a rigid moving object with multiresolution, making it possible to add new details observed
from an approaching object by expanding the pyramid.
Keywords irregular graph pyramid - adaptive representation - object structure - tracking model
Supported by the Austrian Science Fund under grant P18716-N13.
References secured to subscribers.