Method for enhancing panoramic video with stable viewpoint
The invention discloses a panoramic video enhancement method with a stable viewpoint, and the method comprises the following steps: S1, carrying out the perspective projection of a panoramic video in an ERP (Enterprise Resource Planning) format, and obtaining a window with the same field angle as a...
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 | ZOU ZIZHUANG YE MAO |
| description | The invention discloses a panoramic video enhancement method with a stable viewpoint, and the method comprises the following steps: S1, carrying out the perspective projection of a panoramic video in an ERP (Enterprise Resource Planning) format, and obtaining a window with the same field angle as a user; s2, collecting multiple frames of video sequences with the same viewpoint as a training set; s3, taking the 2T + 1 perspective projection frames with the same viewpoint as the input of the enhanced network model, and obtaining a group of features; the features are divided into offset and the importance degree of the offset; fusion is carried out through deformable convolution; and then, after convolution of L layers with the step length being 1, a mask is obtained, and finally, the mask and a target frame At are subjected to addition operation with pixels as units, and a final quality enhancement result is obtained. According to the method, multiple frames of information with the same background are obtained |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116542889A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116542889A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116542889A3</originalsourceid><addsrcrecordid>eNrjZLDyTS3JyE9RSMsvUkjNy0jMS87MS1coSMzLL0rMzUxWKMtMSc1XKM8syVAoLklMykkFiqSWF-Rn5pXwMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQzNTEyMLC0tHY2LUAACKby9Z</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method for enhancing panoramic video with stable viewpoint</title><source>esp@cenet</source><creator>ZOU ZIZHUANG ; YE MAO</creator><creatorcontrib>ZOU ZIZHUANG ; YE MAO</creatorcontrib><description>The invention discloses a panoramic video enhancement method with a stable viewpoint, and the method comprises the following steps: S1, carrying out the perspective projection of a panoramic video in an ERP (Enterprise Resource Planning) format, and obtaining a window with the same field angle as a user; s2, collecting multiple frames of video sequences with the same viewpoint as a training set; s3, taking the 2T + 1 perspective projection frames with the same viewpoint as the input of the enhanced network model, and obtaining a group of features; the features are divided into offset and the importance degree of the offset; fusion is carried out through deformable convolution; and then, after convolution of L layers with the step length being 1, a mask is obtained, and finally, the mask and a target frame At are subjected to addition operation with pixels as units, and a final quality enhancement result is obtained. According to the method, multiple frames of information with the same background are obtained</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC COMMUNICATION TECHNIQUE ; ELECTRICITY ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PICTORIAL COMMUNICATION, e.g. TELEVISION</subject><creationdate>2023</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=20230804&DB=EPODOC&CC=CN&NR=116542889A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230804&DB=EPODOC&CC=CN&NR=116542889A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZOU ZIZHUANG</creatorcontrib><creatorcontrib>YE MAO</creatorcontrib><title>Method for enhancing panoramic video with stable viewpoint</title><description>The invention discloses a panoramic video enhancement method with a stable viewpoint, and the method comprises the following steps: S1, carrying out the perspective projection of a panoramic video in an ERP (Enterprise Resource Planning) format, and obtaining a window with the same field angle as a user; s2, collecting multiple frames of video sequences with the same viewpoint as a training set; s3, taking the 2T + 1 perspective projection frames with the same viewpoint as the input of the enhanced network model, and obtaining a group of features; the features are divided into offset and the importance degree of the offset; fusion is carried out through deformable convolution; and then, after convolution of L layers with the step length being 1, a mask is obtained, and finally, the mask and a target frame At are subjected to addition operation with pixels as units, and a final quality enhancement result is obtained. According to the method, multiple frames of information with the same background are obtained</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC COMMUNICATION TECHNIQUE</subject><subject>ELECTRICITY</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PICTORIAL COMMUNICATION, e.g. TELEVISION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLDyTS3JyE9RSMsvUkjNy0jMS87MS1coSMzLL0rMzUxWKMtMSc1XKM8syVAoLklMykkFiqSWF-Rn5pXwMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQzNTEyMLC0tHY2LUAACKby9Z</recordid><startdate>20230804</startdate><enddate>20230804</enddate><creator>ZOU ZIZHUANG</creator><creator>YE MAO</creator><scope>EVB</scope></search><sort><creationdate>20230804</creationdate><title>Method for enhancing panoramic video with stable viewpoint</title><author>ZOU ZIZHUANG ; YE MAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116542889A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC COMMUNICATION TECHNIQUE</topic><topic>ELECTRICITY</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PICTORIAL COMMUNICATION, e.g. TELEVISION</topic><toplevel>online_resources</toplevel><creatorcontrib>ZOU ZIZHUANG</creatorcontrib><creatorcontrib>YE MAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZOU ZIZHUANG</au><au>YE MAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method for enhancing panoramic video with stable viewpoint</title><date>2023-08-04</date><risdate>2023</risdate><abstract>The invention discloses a panoramic video enhancement method with a stable viewpoint, and the method comprises the following steps: S1, carrying out the perspective projection of a panoramic video in an ERP (Enterprise Resource Planning) format, and obtaining a window with the same field angle as a user; s2, collecting multiple frames of video sequences with the same viewpoint as a training set; s3, taking the 2T + 1 perspective projection frames with the same viewpoint as the input of the enhanced network model, and obtaining a group of features; the features are divided into offset and the importance degree of the offset; fusion is carried out through deformable convolution; and then, after convolution of L layers with the step length being 1, a mask is obtained, and finally, the mask and a target frame At are subjected to addition operation with pixels as units, and a final quality enhancement result is obtained. According to the method, multiple frames of information with the same background are obtained</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116542889A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PICTORIAL COMMUNICATION, e.g. TELEVISION |
| title | Method for enhancing panoramic video with stable viewpoint |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T11%3A19%3A56IST&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=ZOU%20ZIZHUANG&rft.date=2023-08-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116542889A%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 |