1 September 2007 Robust foreground extraction technique using background subtraction with multiple thresholds
Author Affiliations +
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.
© (2007) Society of Photo-Optical Instrumentation Engineers (SPIE)
HanSung Kim, HanSung Kim, Ryuuki Sakamoto, Ryuuki Sakamoto, Itaru Kitahara, Itaru Kitahara, Tomoji Toriyama, Tomoji Toriyama, Kiyoshi Kogure, Kiyoshi Kogure, } "Robust foreground extraction technique using background subtraction with multiple thresholds," Optical Engineering 46(9), 097004 (1 September 2007). https://doi.org/10.1117/1.2779022 . Submission:
JOURNAL ARTICLE
12 PAGES


SHARE
Back to Top