Infrared weak and small target detection method and device based on diffusion model framework

The invention discloses an infrared weak and small target detection method and device based on a diffusion model framework, and the method comprises the steps: inputting a detection image into a trained dual-path coding and decoding neural network model, and predicting the noise in the detection ima...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN JIAXIN, QIN HANLIN, YUAN SHUAI, WANG XINDA, ZHANG XIN, GENG JINNI, WANG JUNYANG
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 CHEN JIAXIN
QIN HANLIN
YUAN SHUAI
WANG XINDA
ZHANG XIN
GENG JINNI
WANG JUNYANG
description The invention discloses an infrared weak and small target detection method and device based on a diffusion model framework, and the method comprises the steps: inputting a detection image into a trained dual-path coding and decoding neural network model, and predicting the noise in the detection image for multiple times through the model, and sequentially subtracting the plurality of predicted noises from the detection image to obtain a target image. The double-path coding and decoding neural network model comprises a plurality of double-path encoders and a resolver, the double-path encoders can extract semantic information and noise features in samples through two feature extraction paths during training, and the resolver can restrain high-frequency noise in the features. Therefore, the dual-path coding and decoding neural network model can fully learn more accurate semantic information and noise features of the sample, the target in the detection image is extracted through the trained dual-path coding and d
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118506009A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118506009A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118506009A3</originalsourceid><addsrcrecordid>eNqNzEEKwjAUBNBsXIh6h-8BhBZRdClF0Y0rt1K-_RMNTZOSRHt9Q_EArmYxb2aq7henAwcIDeCW2AnFjq2lxOGJRIKEJhnvqEN6eRmF4GMa0INj3uVKjNbvOCIvsJQfOww-tHM10WwjFr-cqeXpeKvOK_S-Ruy5gUOqq2tZ7jbFtij2h_U_5gvFZDvr</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Infrared weak and small target detection method and device based on diffusion model framework</title><source>esp@cenet</source><creator>CHEN JIAXIN ; QIN HANLIN ; YUAN SHUAI ; WANG XINDA ; ZHANG XIN ; GENG JINNI ; WANG JUNYANG</creator><creatorcontrib>CHEN JIAXIN ; QIN HANLIN ; YUAN SHUAI ; WANG XINDA ; ZHANG XIN ; GENG JINNI ; WANG JUNYANG</creatorcontrib><description>The invention discloses an infrared weak and small target detection method and device based on a diffusion model framework, and the method comprises the steps: inputting a detection image into a trained dual-path coding and decoding neural network model, and predicting the noise in the detection image for multiple times through the model, and sequentially subtracting the plurality of predicted noises from the detection image to obtain a target image. The double-path coding and decoding neural network model comprises a plurality of double-path encoders and a resolver, the double-path encoders can extract semantic information and noise features in samples through two feature extraction paths during training, and the resolver can restrain high-frequency noise in the features. Therefore, the dual-path coding and decoding neural network model can fully learn more accurate semantic information and noise features of the sample, the target in the detection image is extracted through the trained dual-path coding and d</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=20240816&amp;DB=EPODOC&amp;CC=CN&amp;NR=118506009A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240816&amp;DB=EPODOC&amp;CC=CN&amp;NR=118506009A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN JIAXIN</creatorcontrib><creatorcontrib>QIN HANLIN</creatorcontrib><creatorcontrib>YUAN SHUAI</creatorcontrib><creatorcontrib>WANG XINDA</creatorcontrib><creatorcontrib>ZHANG XIN</creatorcontrib><creatorcontrib>GENG JINNI</creatorcontrib><creatorcontrib>WANG JUNYANG</creatorcontrib><title>Infrared weak and small target detection method and device based on diffusion model framework</title><description>The invention discloses an infrared weak and small target detection method and device based on a diffusion model framework, and the method comprises the steps: inputting a detection image into a trained dual-path coding and decoding neural network model, and predicting the noise in the detection image for multiple times through the model, and sequentially subtracting the plurality of predicted noises from the detection image to obtain a target image. The double-path coding and decoding neural network model comprises a plurality of double-path encoders and a resolver, the double-path encoders can extract semantic information and noise features in samples through two feature extraction paths during training, and the resolver can restrain high-frequency noise in the features. Therefore, the dual-path coding and decoding neural network model can fully learn more accurate semantic information and noise features of the sample, the target in the detection image is extracted through the trained dual-path coding and d</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>eNqNzEEKwjAUBNBsXIh6h-8BhBZRdClF0Y0rt1K-_RMNTZOSRHt9Q_EArmYxb2aq7henAwcIDeCW2AnFjq2lxOGJRIKEJhnvqEN6eRmF4GMa0INj3uVKjNbvOCIvsJQfOww-tHM10WwjFr-cqeXpeKvOK_S-Ruy5gUOqq2tZ7jbFtij2h_U_5gvFZDvr</recordid><startdate>20240816</startdate><enddate>20240816</enddate><creator>CHEN JIAXIN</creator><creator>QIN HANLIN</creator><creator>YUAN SHUAI</creator><creator>WANG XINDA</creator><creator>ZHANG XIN</creator><creator>GENG JINNI</creator><creator>WANG JUNYANG</creator><scope>EVB</scope></search><sort><creationdate>20240816</creationdate><title>Infrared weak and small target detection method and device based on diffusion model framework</title><author>CHEN JIAXIN ; QIN HANLIN ; YUAN SHUAI ; WANG XINDA ; ZHANG XIN ; GENG JINNI ; WANG JUNYANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118506009A3</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>CHEN JIAXIN</creatorcontrib><creatorcontrib>QIN HANLIN</creatorcontrib><creatorcontrib>YUAN SHUAI</creatorcontrib><creatorcontrib>WANG XINDA</creatorcontrib><creatorcontrib>ZHANG XIN</creatorcontrib><creatorcontrib>GENG JINNI</creatorcontrib><creatorcontrib>WANG JUNYANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN JIAXIN</au><au>QIN HANLIN</au><au>YUAN SHUAI</au><au>WANG XINDA</au><au>ZHANG XIN</au><au>GENG JINNI</au><au>WANG JUNYANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Infrared weak and small target detection method and device based on diffusion model framework</title><date>2024-08-16</date><risdate>2024</risdate><abstract>The invention discloses an infrared weak and small target detection method and device based on a diffusion model framework, and the method comprises the steps: inputting a detection image into a trained dual-path coding and decoding neural network model, and predicting the noise in the detection image for multiple times through the model, and sequentially subtracting the plurality of predicted noises from the detection image to obtain a target image. The double-path coding and decoding neural network model comprises a plurality of double-path encoders and a resolver, the double-path encoders can extract semantic information and noise features in samples through two feature extraction paths during training, and the resolver can restrain high-frequency noise in the features. Therefore, the dual-path coding and decoding neural network model can fully learn more accurate semantic information and noise features of the sample, the target in the detection image is extracted through the trained dual-path coding and d</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN118506009A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Infrared weak and small target detection method and device based on diffusion model framework
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T16%3A21%3A45IST&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=CHEN%20JIAXIN&rft.date=2024-08-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118506009A%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