Full metadata record
DC FieldValueLanguage
dc.contributor.authorSun, Shih-Weien_US
dc.contributor.authorWang, Yu-Chiang Franken_US
dc.contributor.authorHuang, Fayen_US
dc.contributor.authorLiao, Hong-Yuan Marken_US
dc.date.accessioned2014-12-08T15:30:21Z-
dc.date.available2014-12-08T15:30:21Z-
dc.date.issued2013-04-01en_US
dc.identifier.issn1047-3203en_US
dc.identifier.urihttp://dx.doi.org/10.1016/j.jvcir.2012.12.003en_US
dc.identifier.urihttp://hdl.handle.net/11536/21702-
dc.description.abstractIn this paper, we present an automatic foreground object detection method for videos captured by freely moving cameras. While we focus on extracting a single foreground object of interest throughout a video sequence, our approach does not require any training data nor the interaction by the users. Based on the SIFT correspondence across video frames, we construct robust SIFT trajectories in terms of the calculated foreground feature point probability. Our foreground feature point probability is able to determine candidate foreground feature points in each frame, without the need of user interaction such as parameter or threshold tuning. Furthermore, we propose a probabilistic consensus foreground object template (CFOT), which is directly applied to the input video for moving object detection via template matching. Our CFOT can be used to detect the foreground object in videos captured by a fast moving camera, even if the contrast between the foreground and background regions is low. Moreover, our proposed method can be generalized to foreground object detection in dynamic backgrounds, and is robust to viewpoint changes across video frames. The contribution of this paper is trifold: (1) we provide a robust decision process to detect the foreground object of interest in videos with contrast and viewpoint variations; (2) our proposed method builds longer SIFT trajectories, and this is shown to be robust and effective for object detection tasks; and (3) the construction of our CFOT is not sensitive to the initial estimation of the foreground region of interest, while its use can achieve excellent foreground object detection results on real-world video data. (c) 2012 Elsevier Inc. All rights reserved.en_US
dc.language.isoen_USen_US
dc.subjectTemplate matchingen_US
dc.subjectObject trackingen_US
dc.subjectVideo object segmentationen_US
dc.subjectForeground segmentationen_US
dc.subjectBackground subtractionen_US
dc.titleMoving foreground object detection via robust SIFT trajectoriesen_US
dc.typeArticleen_US
dc.identifier.doi10.1016/j.jvcir.2012.12.003en_US
dc.identifier.journalJOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATIONen_US
dc.citation.volume24en_US
dc.citation.issue3en_US
dc.citation.spage232en_US
dc.citation.epage243en_US
dc.contributor.department資訊科學與工程研究所zh_TW
dc.contributor.departmentInstitute of Computer Science and Engineeringen_US
dc.identifier.wosnumberWOS:000317149200003-
dc.citation.woscount2-
Appears in Collections:Articles


Files in This Item:

  1. 000317149200003.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.