TY - GEN
T1 - Automatic foreground-background segmentation based on depth from coded aperture
AU - Zhang, Yu Peng
AU - Wang, Yong Tian
AU - Li, Yang
AU - Weng, Dong Dong
PY - 2012
Y1 - 2012
N2 - Foreground-background segmentation is an important problem in computer vision, and it has many applications. We propose a technique of Automatic foreground-background segmentation based on depth from coded aperture. This method first calculates a coarse depth map using technique of coded aperture depth extraction, then estimate the general area of foreground. At last, in order to get the foreground, we use the GrabCut algorithm to segment the image. The entire progress is fully automatic, without any manual intervention. Experiments have proved its effectiveness. And we also did some simple examples for application.
AB - Foreground-background segmentation is an important problem in computer vision, and it has many applications. We propose a technique of Automatic foreground-background segmentation based on depth from coded aperture. This method first calculates a coarse depth map using technique of coded aperture depth extraction, then estimate the general area of foreground. At last, in order to get the foreground, we use the GrabCut algorithm to segment the image. The entire progress is fully automatic, without any manual intervention. Experiments have proved its effectiveness. And we also did some simple examples for application.
KW - Computational Photography
KW - Depth from Coded Aperture
KW - GrabCut
KW - foreground-background segmentation
UR - http://www.scopus.com/inward/record.url?scp=84867535661&partnerID=8YFLogxK
U2 - 10.1109/SOPO.2012.6271104
DO - 10.1109/SOPO.2012.6271104
M3 - Conference contribution
AN - SCOPUS:84867535661
SN - 9781457709111
T3 - 2012 Symposium on Photonics and Optoelectronics, SOPO 2012
BT - 2012 Symposium on Photonics and Optoelectronics, SOPO 2012
T2 - 2012 International Symposium on Photonics and Optoelectronics, SOPO 2012
Y2 - 21 May 2012 through 23 May 2012
ER -