Sciweavers

Share
ICPR
2010
IEEE

Object Tracking with Ratio Cycles Using Shape and Appearance Cues

11 years 11 months ago
Object Tracking with Ratio Cycles Using Shape and Appearance Cues
We present a method for object tracking over time sequence imagery. The image plane is represented with a 4-connected planar graph where vertices are associated with pixels. On each image, the outer contour of the object is localized by finding the optimal cycle in the graph such that a cost function based on temporal, appearance and shape priors is minimized. Our contribution is the particle filtering-based framework to integrate the shape cue with the temporal and appearance cues. We demonstrate that incorporating the shape prior yields promising performance improvement over temporal and appearance priors on various object tracking scenarios.
Mehmet Emre Sargin, Pratim Ghosh, B. S. Manjunath,
Added 04 Mar 2011
Updated 04 Mar 2011
Type Journal
Year 2010
Where ICPR
Authors Mehmet Emre Sargin, Pratim Ghosh, B. S. Manjunath, Kenneth Rose
Comments (0)
books