Share Email Print
cover

Optical Engineering

Robust foreground extraction technique using background subtraction with multiple thresholds
Author(s): HanSung Kim; Ryuuki Sakamoto; Itaru Kitahara; Tomoji Toriyama; Kiyoshi Kogure
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We propose a robust method to extract silhouettes of foreground objects from color-video sequences. To cope with various changes in the background, we model the background as a Laplace distribution and update it with a selective running average and static pixel observation. All pixels in the input video image are classified into four initial regions using background subtraction with multiple thresholds. Shadow regions are eliminated using color components, and the final foreground silhouette is extracted by smoothing the boundaries of the foreground and eliminating errors inside and outside of the regions. Experimental results show that the proposed algorithm works very well in various background and foreground situations.

Paper Details

Date Published: 1 September 2007
PDF: 12 pages
Opt. Eng. 46(9) 097004 doi: 10.1117/1.2779022
Published in: Optical Engineering Volume 46, Issue 9
Show Author Affiliations
HanSung Kim, Advanced Telecommunications Research Institute International (Japan)
Ryuuki Sakamoto, Advanced Telecommunications Research Institute International (Japan)
Itaru Kitahara, Univ. of Tsukuba (Japan)
Tomoji Toriyama, Advanced Telecommunications Research Institute International (Japan)
Kiyoshi Kogure, Advanced Telecommunications Research Institute International (Japan)


© SPIE. Terms of Use
Back to Top