DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jia, JY | ko |
dc.contributor.author | Tai, Yu-Wing | ko |
dc.contributor.author | Wu, TP | ko |
dc.contributor.author | Tang, CK | ko |
dc.date.accessioned | 2011-08-09T04:09:12Z | - |
dc.date.available | 2011-08-09T04:09:12Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2006-05 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.28, no.5, pp.832 - 839 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10203/24805 | - |
dc.description.abstract | This paper presents a complete system capable of synthesizing a large number of pixels that are missing due to occlusion or damage in an uncalibrated input video. These missing pixels may correspond to the static background or cyclic motions of the captured scene. Our system employs user-assisted video layer segmentation, while the main processing in video repair is fully automatic. The input video is first decomposed into the color and illumination videos. The necessary temporal consistency is maintained by tensor voting in the spatio-temporal domain. Missing colors and illumination of the background are synthesized by applying image repairing. Finally, the occluded motions are inferred by spatio-temporal alignment of collected samples at multiple scales. We experimented on our system with some difficult examples with variable illumination, where the capturing camera can be stationary or in motion. | - |
dc.description.sponsorship | The authors would like to thank the associate editor and all of the reviewers for their thorough and constructive suggestions, which were instrumental in improving the quality of the final paper. This research was supported by the Research Grant Council of the Hong Kong Special Administrative Region under grant number HKUST6200/05E and AoE/E-01/99 and the Chinese University of Hong Kong (CUHK) Direct Grant: 2050332. | en |
dc.language | English | - |
dc.language.iso | en_US | en |
dc.publisher | IEEE COMPUTER SOC | - |
dc.subject | IMAGE | - |
dc.subject | INFERENCE | - |
dc.subject | ALIGNMENT | - |
dc.title | Video repairing under variable illumination using cyclic motions | - |
dc.type | Article | - |
dc.identifier.wosid | 000235885700015 | - |
dc.identifier.scopusid | 2-s2.0-33645137026 | - |
dc.type.rims | ART | - |
dc.citation.volume | 28 | - |
dc.citation.issue | 5 | - |
dc.citation.beginningpage | 832 | - |
dc.citation.endingpage | 839 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Tai, Yu-Wing | - |
dc.contributor.nonIdAuthor | Jia, JY | - |
dc.contributor.nonIdAuthor | Wu, TP | - |
dc.contributor.nonIdAuthor | Tang, CK | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | video restoration | - |
dc.subject.keywordAuthor | spatio-temporal consistence | - |
dc.subject.keywordAuthor | illumination consistence | - |
dc.subject.keywordAuthor | tensor voting | - |
dc.subject.keywordAuthor | applications | - |
dc.subject.keywordPlus | IMAGE | - |
dc.subject.keywordPlus | INFERENCE | - |
dc.subject.keywordPlus | ALIGNMENT | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.