For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Multiresolutional Gaussian Mixture Model for Precise and Stable Foreground Segmentation in Transform Domain
Hiroaki TEZUKA Takao NISHITANI
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2009/03/01
Online ISSN: 1745-1337
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Latest Advances in Fundamental Theories of Signal Processing)
foreground segmentation, Gaussian mixture model, fine-to-coarse strategy, Walsh transform, variable block size,
Full Text: PDF>>
This paper describes a multiresolutional Gaussian mixture model (GMM) for precise and stable foreground segmentation. A multiple block sizes GMM and a computationally efficient fine-to-coarse strategy, which are carried out in the Walsh transform (WT) domain, are newly introduced to the GMM scheme. By using a set of variable size block-based GMMs, a precise and stable processing is realized. Our fine-to-coarse strategy comes from the WT spectral nature, which drastically reduces the computational steps. In addition, the total computation amount of the proposed approach requires only less than 10% of the original pixel-based GMM approach. Experimental results show that our approach gives stable performance in many conditions, including dark foreground objects against light, global lighting changes, and scenery in heavy snow.