Video trace removing method and video trace removing device
The invention relates to a video trace removing method and a video trace removing device. The video trace removing method comprises the following steps: acquiring a current frame image and a trace removing area mask of a video; based on the current frame image and the mark removal area mask, obtaini...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | YU BING CHEN YUCONG DAI YURONG WU MINGDA TAO XIN LI FULIN DENG FANBO |
| description | The invention relates to a video trace removing method and a video trace removing device. The video trace removing method comprises the following steps: acquiring a current frame image and a trace removing area mask of a video; based on the current frame image and the mark removal area mask, obtaining a first mark removal result image of the current frame image by utilizing an image mark removal network; obtaining a mark removal result image of a previous frame image of the current frame image of the video; fusing the first trace removal result image of the current frame image and the trace removal result image of the previous frame image to obtain a second trace removal result image of the current frame image, and taking the second trace removal result image as a final trace removal result image of the current frame image.
本公开关于一种视频去痕方法和视频去痕装置，所述视频去痕方法包括：获取视频的当前帧图像和去痕区域掩膜；基于所述当前帧图像和所述去痕区域掩膜，利用图像去痕网络，获得所述当前帧图像的第一去痕结果图像；获取所述视频的所述当前帧图像的前一帧图像的去痕结果图像；对所述当前帧图像的第一去痕结果图像和所述前一帧图像的去痕结果图像进行融合，获得所述当前帧图像的第二去痕结果图像，作为所述当前帧 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN112233055A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN112233055A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN112233055A3</originalsourceid><addsrcrecordid>eNrjZLAOy0xJzVcoKUpMTlUoSs3NL8vMS1fITS3JyE9RSMxLUSjDJp-SWpaZnMrDwJqWmFOcyguluRkU3VxDnD10Uwvy41OLC4Ba8lJL4p39DA2NjIyNDUxNHY2JUQMAl_0vLA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Video trace removing method and video trace removing device</title><source>esp@cenet</source><creator>YU BING ; CHEN YUCONG ; DAI YURONG ; WU MINGDA ; TAO XIN ; LI FULIN ; DENG FANBO</creator><creatorcontrib>YU BING ; CHEN YUCONG ; DAI YURONG ; WU MINGDA ; TAO XIN ; LI FULIN ; DENG FANBO</creatorcontrib><description>The invention relates to a video trace removing method and a video trace removing device. The video trace removing method comprises the following steps: acquiring a current frame image and a trace removing area mask of a video; based on the current frame image and the mark removal area mask, obtaining a first mark removal result image of the current frame image by utilizing an image mark removal network; obtaining a mark removal result image of a previous frame image of the current frame image of the video; fusing the first trace removal result image of the current frame image and the trace removal result image of the previous frame image to obtain a second trace removal result image of the current frame image, and taking the second trace removal result image as a final trace removal result image of the current frame image.
本公开关于一种视频去痕方法和视频去痕装置，所述视频去痕方法包括：获取视频的当前帧图像和去痕区域掩膜；基于所述当前帧图像和所述去痕区域掩膜，利用图像去痕网络，获得所述当前帧图像的第一去痕结果图像；获取所述视频的所述当前帧图像的前一帧图像的去痕结果图像；对所述当前帧图像的第一去痕结果图像和所述前一帧图像的去痕结果图像进行融合，获得所述当前帧图像的第二去痕结果图像，作为所述当前帧</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2021</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210115&DB=EPODOC&CC=CN&NR=112233055A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210115&DB=EPODOC&CC=CN&NR=112233055A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YU BING</creatorcontrib><creatorcontrib>CHEN YUCONG</creatorcontrib><creatorcontrib>DAI YURONG</creatorcontrib><creatorcontrib>WU MINGDA</creatorcontrib><creatorcontrib>TAO XIN</creatorcontrib><creatorcontrib>LI FULIN</creatorcontrib><creatorcontrib>DENG FANBO</creatorcontrib><title>Video trace removing method and video trace removing device</title><description>The invention relates to a video trace removing method and a video trace removing device. The video trace removing method comprises the following steps: acquiring a current frame image and a trace removing area mask of a video; based on the current frame image and the mark removal area mask, obtaining a first mark removal result image of the current frame image by utilizing an image mark removal network; obtaining a mark removal result image of a previous frame image of the current frame image of the video; fusing the first trace removal result image of the current frame image and the trace removal result image of the previous frame image to obtain a second trace removal result image of the current frame image, and taking the second trace removal result image as a final trace removal result image of the current frame image.
本公开关于一种视频去痕方法和视频去痕装置，所述视频去痕方法包括：获取视频的当前帧图像和去痕区域掩膜；基于所述当前帧图像和所述去痕区域掩膜，利用图像去痕网络，获得所述当前帧图像的第一去痕结果图像；获取所述视频的所述当前帧图像的前一帧图像的去痕结果图像；对所述当前帧图像的第一去痕结果图像和所述前一帧图像的去痕结果图像进行融合，获得所述当前帧图像的第二去痕结果图像，作为所述当前帧</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAOy0xJzVcoKUpMTlUoSs3NL8vMS1fITS3JyE9RSMxLUSjDJp-SWpaZnMrDwJqWmFOcyguluRkU3VxDnD10Uwvy41OLC4Ba8lJL4p39DA2NjIyNDUxNHY2JUQMAl_0vLA</recordid><startdate>20210115</startdate><enddate>20210115</enddate><creator>YU BING</creator><creator>CHEN YUCONG</creator><creator>DAI YURONG</creator><creator>WU MINGDA</creator><creator>TAO XIN</creator><creator>LI FULIN</creator><creator>DENG FANBO</creator><scope>EVB</scope></search><sort><creationdate>20210115</creationdate><title>Video trace removing method and video trace removing device</title><author>YU BING ; CHEN YUCONG ; DAI YURONG ; WU MINGDA ; TAO XIN ; LI FULIN ; DENG FANBO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN112233055A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>YU BING</creatorcontrib><creatorcontrib>CHEN YUCONG</creatorcontrib><creatorcontrib>DAI YURONG</creatorcontrib><creatorcontrib>WU MINGDA</creatorcontrib><creatorcontrib>TAO XIN</creatorcontrib><creatorcontrib>LI FULIN</creatorcontrib><creatorcontrib>DENG FANBO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YU BING</au><au>CHEN YUCONG</au><au>DAI YURONG</au><au>WU MINGDA</au><au>TAO XIN</au><au>LI FULIN</au><au>DENG FANBO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Video trace removing method and video trace removing device</title><date>2021-01-15</date><risdate>2021</risdate><abstract>The invention relates to a video trace removing method and a video trace removing device. The video trace removing method comprises the following steps: acquiring a current frame image and a trace removing area mask of a video; based on the current frame image and the mark removal area mask, obtaining a first mark removal result image of the current frame image by utilizing an image mark removal network; obtaining a mark removal result image of a previous frame image of the current frame image of the video; fusing the first trace removal result image of the current frame image and the trace removal result image of the previous frame image to obtain a second trace removal result image of the current frame image, and taking the second trace removal result image as a final trace removal result image of the current frame image.
本公开关于一种视频去痕方法和视频去痕装置，所述视频去痕方法包括：获取视频的当前帧图像和去痕区域掩膜；基于所述当前帧图像和所述去痕区域掩膜，利用图像去痕网络，获得所述当前帧图像的第一去痕结果图像；获取所述视频的所述当前帧图像的前一帧图像的去痕结果图像；对所述当前帧图像的第一去痕结果图像和所述前一帧图像的去痕结果图像进行融合，获得所述当前帧图像的第二去痕结果图像，作为所述当前帧</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN112233055A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Video trace removing method and video trace removing device |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T05%3A57%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=YU%20BING&rft.date=2021-01-15&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN112233055A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |