Share Email Print

Proceedings Paper

Edge noise removal in multimodal background modeling techniques
Author(s): J. W. Choi; S. Apewokin; B. E. Valentine; D. S. Wills; L. M. Wills
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Traditional video scene analysis depends on accurate background modeling techniques to segment objects of interest. Multimodal background models such as Mixture of Gaussian (MOG) and Multimodal Mean (MM) are capable of handling dynamic scene elements and incorporating new objects into the background. Due to the adaptive nature of these techniques, new pixels have to be observed consistently over time before they can be incorporated into the background. However, pixels in the boundary between two colors tend to fluctuate more, creating false positive pixels that result in less accurate foreground segmentation. To correct this, a simple and computationally efficient edge detection based algorithm is proposed. On average, approximately 70 percent of these false positives can be eliminated with little computational overhead.

Paper Details

Date Published: 26 February 2008
PDF: 7 pages
Proc. SPIE 6813, Image Processing: Machine Vision Applications, 68130K (26 February 2008); doi: 10.1117/12.766829
Show Author Affiliations
J. W. Choi, Georgia Institute of Technology (United States)
S. Apewokin, Georgia Institute of Technology (United States)
B. E. Valentine, Georgia Institute of Technology (United States)
D. S. Wills, Georgia Institute of Technology (United States)
L. M. Wills, Georgia Institute of Technology (United States)

Published in SPIE Proceedings Vol. 6813:
Image Processing: Machine Vision Applications
Kurt S. Niel; David Fofi, Editor(s)

© SPIE. Terms of Use
Back to Top