Sciweavers

IWCM
2004
Springer

Tracking Complex Objects Using Graphical Object Models

13 years 8 months ago
Tracking Complex Objects Using Graphical Object Models
We present a probabilistic framework for component-based automatic detection and tracking of objects in video. We represent objects as spatio-temporal two-layer graphical models, where each node corresponds to an object or component of an object at a given time, and the edges correspond to learned spatial and temporal constraints. Object detection and tracking is formulated as inference over a directed loopy graph, and is solved with non-parametric belief propagation. This type of object model allows object-detection to make use of temporal consistency (over an arbitrarily sized temporal window), and facilitates robust tracking of the object. The two layer structure of the graphical model allows inference over the entire object as well as individual components. AdaBoost detectors are used to define the likelihood and form proposal distributions for components. Proposal distributions provide ‘bottomup’ information that is incorporated into the inference process, enabling automatic ...
Leonid Sigal, Ying Zhu, Dorin Comaniciu, Michael J
Added 02 Jul 2010
Updated 02 Jul 2010
Type Conference
Year 2004
Where IWCM
Authors Leonid Sigal, Ying Zhu, Dorin Comaniciu, Michael J. Black
Comments (0)