We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Improving video foreground segmentation with an object-like pool.
- Authors
Xiaoliu Cheng; Wei Lv; Huawei Liu; Xing You; Baoqing Li; Xiaobing Yuan
- 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.
- Subjects
IMAGE segmentation; VIDEO processing; RANDOM fields; PIXELS; FEATURE extraction
- Publication
Journal of Electronic Imaging, 2015, Vol 24, Issue 2, p1
- ISSN
1017-9909
- Publication type
Article
- DOI
10.1117/1.JEI.24.2.023034