Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings   Proceeding details   Article details         Authors         Search    
Adaptive Foreground and Shadow Detection inImage Sequences
Yang Wang, Tele Tan
This paper presents a novel method of foreground segmentation that distinguishes moving objects from their moving cast shadows in monocular image sequences. The models of background, edge information, and shadow are set up and adaptively updated. A Bayesian belief network is proposed to describe the relationships among the segmentation label, background, intensity, and edge information. The notion of Markov random field is used to encourage the spatial connectivity of the segmented regions. The solution is obtained by maximizing the posterior possibility density of the segmentation field.
Pages: 552-559
PS Link:
PDF Link: /papers/02/p552-wang.pdf
AUTHOR = "Yang Wang and Tele Tan",
TITLE = "Adaptive Foreground and Shadow Detection inImage Sequences",
BOOKTITLE = "Proceedings of the Eighteenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-02)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "2002",
PAGES = "552--559"

hosted by DSL   •   site info   •   help