Video De-Fencing
This paper describes and provides an initial solution to a novel video editing task, i.e., video de-fencing. It targets automatic restoration of the video clips that are corrupted by fence-like occlusions during capture. Our key observation lies in the visual parallax between fences and background s...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on circuits and systems for video technology 2014-07, Vol.24 (7), p.1111-1121 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1121 |
|---|---|
| container_issue | 7 |
| container_start_page | 1111 |
| container_title | IEEE transactions on circuits and systems for video technology |
| container_volume | 24 |
| creator | Mu, Yadong Liu, Wei Yan, Shuicheng |
| description | This paper describes and provides an initial solution to a novel video editing task, i.e., video de-fencing. It targets automatic restoration of the video clips that are corrupted by fence-like occlusions during capture. Our key observation lies in the visual parallax between fences and background scenes, which is caused by the fact that the former are typically closer to the camera. Unlike in traditional image inpainting, fence-occluded pixels in the videos tend to appear later in the temporal dimension and are therefore recoverable via optimized pixel selection from relevant frames. To eventually produce fence-free videos, major challenges include cross-frame subpixel image alignment under diverse scene depth, and correct pixel selection that is robust to dominating fence pixels. Several novel tools are developed in this paper, including soft fence detection, weighted truncated optical flow method, and robust temporal median filter. The proposed algorithm is validated on several real-world video clips with fences. |
| doi_str_mv | 10.1109/TCSVT.2013.2241351 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_6415261</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6415261</ieee_id><sourcerecordid>1559699072</sourcerecordid><originalsourceid>FETCH-LOGICAL-c328t-36fec4d24c1b4257b0d7b694bcd49ecdff405106138791e4bb0ea811bfa8f803</originalsourceid><addsrcrecordid>eNpdkD1PwzAQhi0EEqUgMcOCxMKScOfYiT2ilgJSJQairlbsnFGqNilxM_DvcUnFwHQ3PO-HXsZuEFJE0I_l7GNVphwwSzkXmEk8YROUUiWcgzyNP0hMFEd5zi5CWAOgUKKYsOtVU1N3N6dkQa1r2s9LduarTaCr452ycvFczl6T5fvL2-xpmbiMq32S5Z6cqLlwaAWXhYW6sLkW1tVCk6u9FzERcsxUoZGEtUCVQrS-Ul5BNmUPo-2u774GCnuzbYKjzaZqqRuCid11rjUUPKL3_9B1N_RtLBcpERO0LmSk-Ei5vguhJ292fbOt-m-DYA4bmd-NzGEjc9woim5HUUNEf4JcoOTR9wcq0V-D</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1546139975</pqid></control><display><type>article</type><title>Video De-Fencing</title><source>IEEE Electronic Library (IEL)</source><creator>Mu, Yadong ; Liu, Wei ; Yan, Shuicheng</creator><creatorcontrib>Mu, Yadong ; Liu, Wei ; Yan, Shuicheng</creatorcontrib><description>This paper describes and provides an initial solution to a novel video editing task, i.e., video de-fencing. It targets automatic restoration of the video clips that are corrupted by fence-like occlusions during capture. Our key observation lies in the visual parallax between fences and background scenes, which is caused by the fact that the former are typically closer to the camera. Unlike in traditional image inpainting, fence-occluded pixels in the videos tend to appear later in the temporal dimension and are therefore recoverable via optimized pixel selection from relevant frames. To eventually produce fence-free videos, major challenges include cross-frame subpixel image alignment under diverse scene depth, and correct pixel selection that is robust to dominating fence pixels. Several novel tools are developed in this paper, including soft fence detection, weighted truncated optical flow method, and robust temporal median filter. The proposed algorithm is validated on several real-world video clips with fences.</description><identifier>ISSN: 1051-8215</identifier><identifier>EISSN: 1558-2205</identifier><identifier>DOI: 10.1109/TCSVT.2013.2241351</identifier><identifier>CODEN: ITCTEM</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Cameras ; Clips ; Estimation ; Fences ; Image restoration ; Optical imaging ; Parallax ; Pixels ; Rain ; Robustness ; sub-pixel alignment ; Tasks ; Temporal logic ; Video de-fencing ; Visual ; Visualization ; weighted truncated optical flow</subject><ispartof>IEEE transactions on circuits and systems for video technology, 2014-07, Vol.24 (7), p.1111-1121</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Jul 2014</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c328t-36fec4d24c1b4257b0d7b694bcd49ecdff405106138791e4bb0ea811bfa8f803</citedby><cites>FETCH-LOGICAL-c328t-36fec4d24c1b4257b0d7b694bcd49ecdff405106138791e4bb0ea811bfa8f803</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6415261$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6415261$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Mu, Yadong</creatorcontrib><creatorcontrib>Liu, Wei</creatorcontrib><creatorcontrib>Yan, Shuicheng</creatorcontrib><title>Video De-Fencing</title><title>IEEE transactions on circuits and systems for video technology</title><addtitle>TCSVT</addtitle><description>This paper describes and provides an initial solution to a novel video editing task, i.e., video de-fencing. It targets automatic restoration of the video clips that are corrupted by fence-like occlusions during capture. Our key observation lies in the visual parallax between fences and background scenes, which is caused by the fact that the former are typically closer to the camera. Unlike in traditional image inpainting, fence-occluded pixels in the videos tend to appear later in the temporal dimension and are therefore recoverable via optimized pixel selection from relevant frames. To eventually produce fence-free videos, major challenges include cross-frame subpixel image alignment under diverse scene depth, and correct pixel selection that is robust to dominating fence pixels. Several novel tools are developed in this paper, including soft fence detection, weighted truncated optical flow method, and robust temporal median filter. The proposed algorithm is validated on several real-world video clips with fences.</description><subject>Cameras</subject><subject>Clips</subject><subject>Estimation</subject><subject>Fences</subject><subject>Image restoration</subject><subject>Optical imaging</subject><subject>Parallax</subject><subject>Pixels</subject><subject>Rain</subject><subject>Robustness</subject><subject>sub-pixel alignment</subject><subject>Tasks</subject><subject>Temporal logic</subject><subject>Video de-fencing</subject><subject>Visual</subject><subject>Visualization</subject><subject>weighted truncated optical flow</subject><issn>1051-8215</issn><issn>1558-2205</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkD1PwzAQhi0EEqUgMcOCxMKScOfYiT2ilgJSJQairlbsnFGqNilxM_DvcUnFwHQ3PO-HXsZuEFJE0I_l7GNVphwwSzkXmEk8YROUUiWcgzyNP0hMFEd5zi5CWAOgUKKYsOtVU1N3N6dkQa1r2s9LduarTaCr452ycvFczl6T5fvL2-xpmbiMq32S5Z6cqLlwaAWXhYW6sLkW1tVCk6u9FzERcsxUoZGEtUCVQrS-Ul5BNmUPo-2u774GCnuzbYKjzaZqqRuCid11rjUUPKL3_9B1N_RtLBcpERO0LmSk-Ei5vguhJ292fbOt-m-DYA4bmd-NzGEjc9woim5HUUNEf4JcoOTR9wcq0V-D</recordid><startdate>20140701</startdate><enddate>20140701</enddate><creator>Mu, Yadong</creator><creator>Liu, Wei</creator><creator>Yan, Shuicheng</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20140701</creationdate><title>Video De-Fencing</title><author>Mu, Yadong ; Liu, Wei ; Yan, Shuicheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c328t-36fec4d24c1b4257b0d7b694bcd49ecdff405106138791e4bb0ea811bfa8f803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Cameras</topic><topic>Clips</topic><topic>Estimation</topic><topic>Fences</topic><topic>Image restoration</topic><topic>Optical imaging</topic><topic>Parallax</topic><topic>Pixels</topic><topic>Rain</topic><topic>Robustness</topic><topic>sub-pixel alignment</topic><topic>Tasks</topic><topic>Temporal logic</topic><topic>Video de-fencing</topic><topic>Visual</topic><topic>Visualization</topic><topic>weighted truncated optical flow</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mu, Yadong</creatorcontrib><creatorcontrib>Liu, Wei</creatorcontrib><creatorcontrib>Yan, Shuicheng</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on circuits and systems for video technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Mu, Yadong</au><au>Liu, Wei</au><au>Yan, Shuicheng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Video De-Fencing</atitle><jtitle>IEEE transactions on circuits and systems for video technology</jtitle><stitle>TCSVT</stitle><date>2014-07-01</date><risdate>2014</risdate><volume>24</volume><issue>7</issue><spage>1111</spage><epage>1121</epage><pages>1111-1121</pages><issn>1051-8215</issn><eissn>1558-2205</eissn><coden>ITCTEM</coden><abstract>This paper describes and provides an initial solution to a novel video editing task, i.e., video de-fencing. It targets automatic restoration of the video clips that are corrupted by fence-like occlusions during capture. Our key observation lies in the visual parallax between fences and background scenes, which is caused by the fact that the former are typically closer to the camera. Unlike in traditional image inpainting, fence-occluded pixels in the videos tend to appear later in the temporal dimension and are therefore recoverable via optimized pixel selection from relevant frames. To eventually produce fence-free videos, major challenges include cross-frame subpixel image alignment under diverse scene depth, and correct pixel selection that is robust to dominating fence pixels. Several novel tools are developed in this paper, including soft fence detection, weighted truncated optical flow method, and robust temporal median filter. The proposed algorithm is validated on several real-world video clips with fences.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TCSVT.2013.2241351</doi><tpages>11</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1051-8215 |
| ispartof | IEEE transactions on circuits and systems for video technology, 2014-07, Vol.24 (7), p.1111-1121 |
| issn | 1051-8215 1558-2205 |
| language | eng |
| recordid | cdi_ieee_primary_6415261 |
| source | IEEE Electronic Library (IEL) |
| subjects | Cameras Clips Estimation Fences Image restoration Optical imaging Parallax Pixels Rain Robustness sub-pixel alignment Tasks Temporal logic Video de-fencing Visual Visualization weighted truncated optical flow |
| title | Video De-Fencing |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T05%3A23%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Video%20De-Fencing&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems%20for%20video%20technology&rft.au=Mu,%20Yadong&rft.date=2014-07-01&rft.volume=24&rft.issue=7&rft.spage=1111&rft.epage=1121&rft.pages=1111-1121&rft.issn=1051-8215&rft.eissn=1558-2205&rft.coden=ITCTEM&rft_id=info:doi/10.1109/TCSVT.2013.2241351&rft_dat=%3Cproquest_RIE%3E1559699072%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1546139975&rft_id=info:pmid/&rft_ieee_id=6415261&rfr_iscdi=true |