Sciweavers

CVPR
2010
IEEE

A probabilistic framework for joint segmentation and tracking

14 years 19 days ago
A probabilistic framework for joint segmentation and tracking
Most tracking algorithms implicitly apply a coarse segmentation of each target object using a simple mask such as a rectangle or an ellipse. Although convenient, such coarse segmentation results in several problems in tracking—drift, switching of targets, poor target localization, to name a few—since it inherently includes extra non-target pixels if the mask is larger than the target or excludes some portion of target pixels if the mask is smaller than the target. In this paper, we propose a novel probabilistic framework for jointly solving segmentation and tracking. Starting from a joint Gaussian distribution over all the pixels, candidate target locations are evaluated by first computing a pixel-level segmentation and then explicitly including this segmentation in the probability model. The segmentation is also used to incrementally update the probability model based on a modified probabilistic principal component analysis (PPCA). Our experimental results show that the propose...
Chad Aeschliman, Johnny Park, Avinash C. Kak
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where CVPR
Authors Chad Aeschliman, Johnny Park, Avinash C. Kak
Comments (0)