Feature enhancement and short-term memory combined remote sensing small target tracking method and device

The invention provides a remote sensing small target tracking method and device combining feature enhancement and short-term memory, and relates to the field of remote sensing target tracking, and the method comprises the steps: obtaining target video data, building a target tracking frame through e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WANG LEI, LI ZHAOMING, FENG RUI, LIN CUNBAO, WANG LI, YANG XINYAN
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 WANG LEI
LI ZHAOMING
FENG RUI
LIN CUNBAO
WANG LI
YANG XINYAN
description The invention provides a remote sensing small target tracking method and device combining feature enhancement and short-term memory, and relates to the field of remote sensing target tracking, and the method comprises the steps: obtaining target video data, building a target tracking frame through employing a KCF algorithm, reading a video frame sequence of the target video data, determining a first frame target candidate region, and obtaining a second frame target candidate region; and based on the first frame of target candidate region, carrying out adaptive guide filtering, extracting LOG edge features and HOG gradient features, inputting the LOG edge features and the HOG gradient features into a target tracking framework to obtain a KCF feature fusion tracking result, then carrying out shielding judgment on the target by using a short-time tracking state memory strategy, and when the judgment result is that shielding exists, carrying out target tracking. And updating the filter template by adopting a shor
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117830659A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117830659A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117830659A3</originalsourceid><addsrcrecordid>eNqNjEsKwkAQBbNxIeod2gMEDEGNSwkGV67ch3bmmQxmesJMK3h7P3gAV48qijfNXAPWewRBehYDD1FisZT6EDVXRE8ePsQnmeAvTmApvllBCZKcdJQ8DwMpxw5KGtncPtZD-2C_VxYPZzDPJlceEha_nWXL5nCujznG0CKNbCDQtj4VxbYqV5v1bl_-07wAfq1BDg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Feature enhancement and short-term memory combined remote sensing small target tracking method and device</title><source>esp@cenet</source><creator>WANG LEI ; LI ZHAOMING ; FENG RUI ; LIN CUNBAO ; WANG LI ; YANG XINYAN</creator><creatorcontrib>WANG LEI ; LI ZHAOMING ; FENG RUI ; LIN CUNBAO ; WANG LI ; YANG XINYAN</creatorcontrib><description>The invention provides a remote sensing small target tracking method and device combining feature enhancement and short-term memory, and relates to the field of remote sensing target tracking, and the method comprises the steps: obtaining target video data, building a target tracking frame through employing a KCF algorithm, reading a video frame sequence of the target video data, determining a first frame target candidate region, and obtaining a second frame target candidate region; and based on the first frame of target candidate region, carrying out adaptive guide filtering, extracting LOG edge features and HOG gradient features, inputting the LOG edge features and the HOG gradient features into a target tracking framework to obtain a KCF feature fusion tracking result, then carrying out shielding judgment on the target by using a short-time tracking state memory strategy, and when the judgment result is that shielding exists, carrying out target tracking. And updating the filter template by adopting a shor</description><language>chi ; eng</language><subject>CALCULATING ; 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=20240405&amp;DB=EPODOC&amp;CC=CN&amp;NR=117830659A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240405&amp;DB=EPODOC&amp;CC=CN&amp;NR=117830659A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG LEI</creatorcontrib><creatorcontrib>LI ZHAOMING</creatorcontrib><creatorcontrib>FENG RUI</creatorcontrib><creatorcontrib>LIN CUNBAO</creatorcontrib><creatorcontrib>WANG LI</creatorcontrib><creatorcontrib>YANG XINYAN</creatorcontrib><title>Feature enhancement and short-term memory combined remote sensing small target tracking method and device</title><description>The invention provides a remote sensing small target tracking method and device combining feature enhancement and short-term memory, and relates to the field of remote sensing target tracking, and the method comprises the steps: obtaining target video data, building a target tracking frame through employing a KCF algorithm, reading a video frame sequence of the target video data, determining a first frame target candidate region, and obtaining a second frame target candidate region; and based on the first frame of target candidate region, carrying out adaptive guide filtering, extracting LOG edge features and HOG gradient features, inputting the LOG edge features and the HOG gradient features into a target tracking framework to obtain a KCF feature fusion tracking result, then carrying out shielding judgment on the target by using a short-time tracking state memory strategy, and when the judgment result is that shielding exists, carrying out target tracking. And updating the filter template by adopting a shor</description><subject>CALCULATING</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>eNqNjEsKwkAQBbNxIeod2gMEDEGNSwkGV67ch3bmmQxmesJMK3h7P3gAV48qijfNXAPWewRBehYDD1FisZT6EDVXRE8ePsQnmeAvTmApvllBCZKcdJQ8DwMpxw5KGtncPtZD-2C_VxYPZzDPJlceEha_nWXL5nCujznG0CKNbCDQtj4VxbYqV5v1bl_-07wAfq1BDg</recordid><startdate>20240405</startdate><enddate>20240405</enddate><creator>WANG LEI</creator><creator>LI ZHAOMING</creator><creator>FENG RUI</creator><creator>LIN CUNBAO</creator><creator>WANG LI</creator><creator>YANG XINYAN</creator><scope>EVB</scope></search><sort><creationdate>20240405</creationdate><title>Feature enhancement and short-term memory combined remote sensing small target tracking method and device</title><author>WANG LEI ; LI ZHAOMING ; FENG RUI ; LIN CUNBAO ; WANG LI ; YANG XINYAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117830659A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG LEI</creatorcontrib><creatorcontrib>LI ZHAOMING</creatorcontrib><creatorcontrib>FENG RUI</creatorcontrib><creatorcontrib>LIN CUNBAO</creatorcontrib><creatorcontrib>WANG LI</creatorcontrib><creatorcontrib>YANG XINYAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG LEI</au><au>LI ZHAOMING</au><au>FENG RUI</au><au>LIN CUNBAO</au><au>WANG LI</au><au>YANG XINYAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Feature enhancement and short-term memory combined remote sensing small target tracking method and device</title><date>2024-04-05</date><risdate>2024</risdate><abstract>The invention provides a remote sensing small target tracking method and device combining feature enhancement and short-term memory, and relates to the field of remote sensing target tracking, and the method comprises the steps: obtaining target video data, building a target tracking frame through employing a KCF algorithm, reading a video frame sequence of the target video data, determining a first frame target candidate region, and obtaining a second frame target candidate region; and based on the first frame of target candidate region, carrying out adaptive guide filtering, extracting LOG edge features and HOG gradient features, inputting the LOG edge features and the HOG gradient features into a target tracking framework to obtain a KCF feature fusion tracking result, then carrying out shielding judgment on the target by using a short-time tracking state memory strategy, and when the judgment result is that shielding exists, carrying out target tracking. And updating the filter template by adopting a shor</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117830659A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title Feature enhancement and short-term memory combined remote sensing small target tracking method and device
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T14%3A46%3A22IST&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=WANG%20LEI&rft.date=2024-04-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117830659A%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