Share Email Print
cover

Journal of Electronic Imaging • Open Access

Improving video foreground segmentation with an object-like pool
Author(s): Xiaoliu Cheng; Wei Lv; Huawei Liu; Xing You; Baoqing Li; Xiaobing Yuan

Paper Abstract

Foreground segmentation in video frames is quite valuable for object and activity recognition, while the existing approaches often demand training data or initial annotation, which is expensive and inconvenient. We propose an automatic and unsupervised method of foreground segmentation given an unlabeled and short video. The pixel-level optical flow and binary mask features are converted into the normal probabilistic superpixels, therefore, they are adaptable to build the superpixel-level conditional random field which aims to label the foreground and background. We exploit the fact that the appearance and motion features of the moving object are temporally and spatially coherent in general, to construct an object-like pool and background-like pool via the previous segmented results. The continuously updated pools can be regarded as the “prior” knowledge of the current frame to provide a reliable way to learn the features of the object. Experimental results demonstrate that our approach exceeds the current methods, both qualitatively and quantitatively.

Paper Details

Date Published: 23 April 2015
PDF: 8 pages
J. Electron. Imaging. 24(2) 023034 doi: 10.1117/1.JEI.24.2.023034
Published in: Journal of Electronic Imaging Volume 24, Issue 2
Show Author Affiliations
Xiaoliu Cheng, Chinese Academy of Sciences (China)
Univ. of Chinese Academy of Sciences (China)
Wei Lv, Chinese Academy of Sciences (China)
Huawei Liu, Chinese Academy of Sciences (China)
Univ. of Chinese Academy of Sciences (China)
Xing You, Chinese Academy of Sciences (China)
Univ. of Chinese Academy of Sciences (China)
Baoqing Li, Chinese Academy of Sciences (China)
Xiaobing Yuan, Chinese Academy of Sciences (China)


© SPIE. Terms of Use
Back to Top