期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 22, 期 7, 页码 2600-2610出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2013.2253483
关键词
Conditional random field (CRF); video object extraction (VOE); visual saliency
资金
- National Science Council of Taiwan [NSC 99-2221-E-001-020, NSC 100-2221-E-001-018-MY2]
This paper presents a saliency-based video object extraction (VOE) framework. The proposed framework aims to automatically extract foreground objects of interest without any user interaction or the use of any training data (i.e., not limited to any particular type of object). To separate foreground and background regions within and across video frames, the proposed method utilizes visual and motion saliency information extracted from the input video. A conditional random field is applied to effectively combine the saliency induced features, which allows us to deal with unknown pose and scale variations of the foreground object (and its articulated parts). Based on the ability to preserve both spatial continuity and temporal consistency in the proposed VOE framework, experiments on a variety of videos verify that our method is able to produce quantitatively and qualitatively satisfactory VOE results.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据