Sciweavers

Share
CVPR
2003
IEEE

Probabilistic Tracking in Joint Feature-Spatial Spaces

10 years 4 months ago
Probabilistic Tracking in Joint Feature-Spatial Spaces
In this paper we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object as a probabilistic constraint to track that region over time. The tracking is achieved by maximizing a similaritybased objective function over transformation space given a nonparametric representation of the joint feature-spatial distribution. Such a representation imposes a probabilistic constraint on the region feature distribution coupled with the region structure which yields an appearance tracker that is robust to small local deformations and partial occlusion. We present the approach for the general form of joint feature-spatial distributions and apply it to tracking with different types of image features including row intensity, color and image gradient.
Ahmed M. Elgammal, Ramani Duraiswami, Larry S. Dav
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2003
Where CVPR
Authors Ahmed M. Elgammal, Ramani Duraiswami, Larry S. Davis
Comments (0)
books