Video image fusion method based on space-time grid

The invention relates to the technical field of video image fusion, in particular to a video image fusion method based on a space-time grid, which comprises the following steps of: performing a network event related video collection technology on videos through a CNN (Convolutional Neural Network) t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: YAO HAIPENG, QI FENG, XI TIEYIN, DAI DONG, CHAI SHAOFU, CHENG LI, WEI FENGSHA, LUO WEILI, ZHAO YANG
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 YAO HAIPENG
QI FENG
XI TIEYIN
DAI DONG
CHAI SHAOFU
CHENG LI
WEI FENGSHA
LUO WEILI
ZHAO YANG
description The invention relates to the technical field of video image fusion, in particular to a video image fusion method based on a space-time grid, which comprises the following steps of: performing a network event related video collection technology on videos through a CNN (Convolutional Neural Network) technology, realizing regional alignment and space-time alignment by using space-time grid coding, collecting related videos, performing video segmentation arrangement through the CNN technology, and performing video segmentation arrangement through the CNN technology. Whether input video data of the videos processed by the CNN technology conform to the same event point is judged, a person inputs a more specific time range and event characteristics of the event point into the GAN technology, and then whether the input video data of the videos processed by the CNN technology conform to the same event point is judged; and finally, the fused video is identified and analyzed through a video event point feature identific
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117975213A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117975213A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117975213A3</originalsourceid><addsrcrecordid>eNrjZDAKy0xJzVfIzE1MT1VIKy3OzM9TyE0tychPUUhKLE5NUQDyiwsSk1N1SzJzUxXSizJTeBhY0xJzilN5oTQ3g6Kba4izh25qQX58KlhxXmpJvLOfoaG5pbmpkaGxozExagCIWCt6</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Video image fusion method based on space-time grid</title><source>esp@cenet</source><creator>YAO HAIPENG ; QI FENG ; XI TIEYIN ; DAI DONG ; CHAI SHAOFU ; CHENG LI ; WEI FENGSHA ; LUO WEILI ; ZHAO YANG</creator><creatorcontrib>YAO HAIPENG ; QI FENG ; XI TIEYIN ; DAI DONG ; CHAI SHAOFU ; CHENG LI ; WEI FENGSHA ; LUO WEILI ; ZHAO YANG</creatorcontrib><description>The invention relates to the technical field of video image fusion, in particular to a video image fusion method based on a space-time grid, which comprises the following steps of: performing a network event related video collection technology on videos through a CNN (Convolutional Neural Network) technology, realizing regional alignment and space-time alignment by using space-time grid coding, collecting related videos, performing video segmentation arrangement through the CNN technology, and performing video segmentation arrangement through the CNN technology. Whether input video data of the videos processed by the CNN technology conform to the same event point is judged, a person inputs a more specific time range and event characteristics of the event point into the GAN technology, and then whether the input video data of the videos processed by the CNN technology conform to the same event point is judged; and finally, the fused video is identified and analyzed through a video event point feature identific</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</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&amp;date=20240503&amp;DB=EPODOC&amp;CC=CN&amp;NR=117975213A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25568,76551</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240503&amp;DB=EPODOC&amp;CC=CN&amp;NR=117975213A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YAO HAIPENG</creatorcontrib><creatorcontrib>QI FENG</creatorcontrib><creatorcontrib>XI TIEYIN</creatorcontrib><creatorcontrib>DAI DONG</creatorcontrib><creatorcontrib>CHAI SHAOFU</creatorcontrib><creatorcontrib>CHENG LI</creatorcontrib><creatorcontrib>WEI FENGSHA</creatorcontrib><creatorcontrib>LUO WEILI</creatorcontrib><creatorcontrib>ZHAO YANG</creatorcontrib><title>Video image fusion method based on space-time grid</title><description>The invention relates to the technical field of video image fusion, in particular to a video image fusion method based on a space-time grid, which comprises the following steps of: performing a network event related video collection technology on videos through a CNN (Convolutional Neural Network) technology, realizing regional alignment and space-time alignment by using space-time grid coding, collecting related videos, performing video segmentation arrangement through the CNN technology, and performing video segmentation arrangement through the CNN technology. Whether input video data of the videos processed by the CNN technology conform to the same event point is judged, a person inputs a more specific time range and event characteristics of the event point into the GAN technology, and then whether the input video data of the videos processed by the CNN technology conform to the same event point is judged; and finally, the fused video is identified and analyzed through a video event point feature identific</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDAKy0xJzVfIzE1MT1VIKy3OzM9TyE0tychPUUhKLE5NUQDyiwsSk1N1SzJzUxXSizJTeBhY0xJzilN5oTQ3g6Kba4izh25qQX58KlhxXmpJvLOfoaG5pbmpkaGxozExagCIWCt6</recordid><startdate>20240503</startdate><enddate>20240503</enddate><creator>YAO HAIPENG</creator><creator>QI FENG</creator><creator>XI TIEYIN</creator><creator>DAI DONG</creator><creator>CHAI SHAOFU</creator><creator>CHENG LI</creator><creator>WEI FENGSHA</creator><creator>LUO WEILI</creator><creator>ZHAO YANG</creator><scope>EVB</scope></search><sort><creationdate>20240503</creationdate><title>Video image fusion method based on space-time grid</title><author>YAO HAIPENG ; QI FENG ; XI TIEYIN ; DAI DONG ; CHAI SHAOFU ; CHENG LI ; WEI FENGSHA ; LUO WEILI ; ZHAO YANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117975213A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>YAO HAIPENG</creatorcontrib><creatorcontrib>QI FENG</creatorcontrib><creatorcontrib>XI TIEYIN</creatorcontrib><creatorcontrib>DAI DONG</creatorcontrib><creatorcontrib>CHAI SHAOFU</creatorcontrib><creatorcontrib>CHENG LI</creatorcontrib><creatorcontrib>WEI FENGSHA</creatorcontrib><creatorcontrib>LUO WEILI</creatorcontrib><creatorcontrib>ZHAO YANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YAO HAIPENG</au><au>QI FENG</au><au>XI TIEYIN</au><au>DAI DONG</au><au>CHAI SHAOFU</au><au>CHENG LI</au><au>WEI FENGSHA</au><au>LUO WEILI</au><au>ZHAO YANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Video image fusion method based on space-time grid</title><date>2024-05-03</date><risdate>2024</risdate><abstract>The invention relates to the technical field of video image fusion, in particular to a video image fusion method based on a space-time grid, which comprises the following steps of: performing a network event related video collection technology on videos through a CNN (Convolutional Neural Network) technology, realizing regional alignment and space-time alignment by using space-time grid coding, collecting related videos, performing video segmentation arrangement through the CNN technology, and performing video segmentation arrangement through the CNN technology. Whether input video data of the videos processed by the CNN technology conform to the same event point is judged, a person inputs a more specific time range and event characteristics of the event point into the GAN technology, and then whether the input video data of the videos processed by the CNN technology conform to the same event point is judged; and finally, the fused video is identified and analyzed through a video event point feature identific</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117975213A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Video image fusion method based on space-time grid
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-16T23%3A09%3A11IST&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=YAO%20HAIPENG&rft.date=2024-05-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117975213A%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