Pyramid neural network image defogging method and system based on end-to-end multi-size fusion
The invention discloses a pyramid neural network image defogging method and system based on end-to-end multi-size fusion. Five groups of feature maps of a foggy image in different sizes and sub-regions are extracted by using a backbone network in an image defogging model; performing feature enhancem...
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 | CAI RONGHUI HUANG JINGUI WANG SHENGCHUN CHEN PEIQI GE JINGJING LUO YINGGUANG YE CHENGZHI TIAN BIN LIU LIANYE JI JUNWEI |
| description | The invention discloses a pyramid neural network image defogging method and system based on end-to-end multi-size fusion. Five groups of feature maps of a foggy image in different sizes and sub-regions are extracted by using a backbone network in an image defogging model; performing feature enhancement on the five groups of feature maps by using a feature pyramid network structure in the image defogging model to obtain five groups of feature maps after feature enhancement; fusing the five groups of feature maps through a spatial multi-size feature superposition fusion method to obtain fused features; a decoder in the image defogging model is used for further fusing and decoding the fused features to obtain intermediate estimation parameters of the network; and reconstructing the network intermediate estimation parameter and an original foggy image input by the network by using a physical recovery module to obtain a fogless image. According to the method, the local features and the global features can be fused |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115063304A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115063304A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115063304A3</originalsourceid><addsrcrecordid>eNqNzbEKwjAQgOEuDqK-w_kAgZaouxTFSRycLae5xsMmV3oJUp_eDj6A07f88M-L22UcMLCDSHnAbiK9ZXgBB_QEjlrxnqOHQOkpDjA60FETBbijkgOJQNGZJGYCQu4SG-UPQZuVJS6LWYud0urnolgfD9f6ZKiXhrTHB03Hpj5X1bbcWVtu9vaf5gspFzxO</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Pyramid neural network image defogging method and system based on end-to-end multi-size fusion</title><source>esp@cenet</source><creator>CAI RONGHUI ; HUANG JINGUI ; WANG SHENGCHUN ; CHEN PEIQI ; GE JINGJING ; LUO YINGGUANG ; YE CHENGZHI ; TIAN BIN ; LIU LIANYE ; JI JUNWEI</creator><creatorcontrib>CAI RONGHUI ; HUANG JINGUI ; WANG SHENGCHUN ; CHEN PEIQI ; GE JINGJING ; LUO YINGGUANG ; YE CHENGZHI ; TIAN BIN ; LIU LIANYE ; JI JUNWEI</creatorcontrib><description>The invention discloses a pyramid neural network image defogging method and system based on end-to-end multi-size fusion. Five groups of feature maps of a foggy image in different sizes and sub-regions are extracted by using a backbone network in an image defogging model; performing feature enhancement on the five groups of feature maps by using a feature pyramid network structure in the image defogging model to obtain five groups of feature maps after feature enhancement; fusing the five groups of feature maps through a spatial multi-size feature superposition fusion method to obtain fused features; a decoder in the image defogging model is used for further fusing and decoding the fused features to obtain intermediate estimation parameters of the network; and reconstructing the network intermediate estimation parameter and an original foggy image input by the network by using a physical recovery module to obtain a fogless image. According to the method, the local features and the global features can be fused</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2022</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=20220916&DB=EPODOC&CC=CN&NR=115063304A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220916&DB=EPODOC&CC=CN&NR=115063304A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CAI RONGHUI</creatorcontrib><creatorcontrib>HUANG JINGUI</creatorcontrib><creatorcontrib>WANG SHENGCHUN</creatorcontrib><creatorcontrib>CHEN PEIQI</creatorcontrib><creatorcontrib>GE JINGJING</creatorcontrib><creatorcontrib>LUO YINGGUANG</creatorcontrib><creatorcontrib>YE CHENGZHI</creatorcontrib><creatorcontrib>TIAN BIN</creatorcontrib><creatorcontrib>LIU LIANYE</creatorcontrib><creatorcontrib>JI JUNWEI</creatorcontrib><title>Pyramid neural network image defogging method and system based on end-to-end multi-size fusion</title><description>The invention discloses a pyramid neural network image defogging method and system based on end-to-end multi-size fusion. Five groups of feature maps of a foggy image in different sizes and sub-regions are extracted by using a backbone network in an image defogging model; performing feature enhancement on the five groups of feature maps by using a feature pyramid network structure in the image defogging model to obtain five groups of feature maps after feature enhancement; fusing the five groups of feature maps through a spatial multi-size feature superposition fusion method to obtain fused features; a decoder in the image defogging model is used for further fusing and decoding the fused features to obtain intermediate estimation parameters of the network; and reconstructing the network intermediate estimation parameter and an original foggy image input by the network by using a physical recovery module to obtain a fogless image. According to the method, the local features and the global features can be fused</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNzbEKwjAQgOEuDqK-w_kAgZaouxTFSRycLae5xsMmV3oJUp_eDj6A07f88M-L22UcMLCDSHnAbiK9ZXgBB_QEjlrxnqOHQOkpDjA60FETBbijkgOJQNGZJGYCQu4SG-UPQZuVJS6LWYud0urnolgfD9f6ZKiXhrTHB03Hpj5X1bbcWVtu9vaf5gspFzxO</recordid><startdate>20220916</startdate><enddate>20220916</enddate><creator>CAI RONGHUI</creator><creator>HUANG JINGUI</creator><creator>WANG SHENGCHUN</creator><creator>CHEN PEIQI</creator><creator>GE JINGJING</creator><creator>LUO YINGGUANG</creator><creator>YE CHENGZHI</creator><creator>TIAN BIN</creator><creator>LIU LIANYE</creator><creator>JI JUNWEI</creator><scope>EVB</scope></search><sort><creationdate>20220916</creationdate><title>Pyramid neural network image defogging method and system based on end-to-end multi-size fusion</title><author>CAI RONGHUI ; HUANG JINGUI ; WANG SHENGCHUN ; CHEN PEIQI ; GE JINGJING ; LUO YINGGUANG ; YE CHENGZHI ; TIAN BIN ; LIU LIANYE ; JI JUNWEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115063304A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CAI RONGHUI</creatorcontrib><creatorcontrib>HUANG JINGUI</creatorcontrib><creatorcontrib>WANG SHENGCHUN</creatorcontrib><creatorcontrib>CHEN PEIQI</creatorcontrib><creatorcontrib>GE JINGJING</creatorcontrib><creatorcontrib>LUO YINGGUANG</creatorcontrib><creatorcontrib>YE CHENGZHI</creatorcontrib><creatorcontrib>TIAN BIN</creatorcontrib><creatorcontrib>LIU LIANYE</creatorcontrib><creatorcontrib>JI JUNWEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CAI RONGHUI</au><au>HUANG JINGUI</au><au>WANG SHENGCHUN</au><au>CHEN PEIQI</au><au>GE JINGJING</au><au>LUO YINGGUANG</au><au>YE CHENGZHI</au><au>TIAN BIN</au><au>LIU LIANYE</au><au>JI JUNWEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Pyramid neural network image defogging method and system based on end-to-end multi-size fusion</title><date>2022-09-16</date><risdate>2022</risdate><abstract>The invention discloses a pyramid neural network image defogging method and system based on end-to-end multi-size fusion. Five groups of feature maps of a foggy image in different sizes and sub-regions are extracted by using a backbone network in an image defogging model; performing feature enhancement on the five groups of feature maps by using a feature pyramid network structure in the image defogging model to obtain five groups of feature maps after feature enhancement; fusing the five groups of feature maps through a spatial multi-size feature superposition fusion method to obtain fused features; a decoder in the image defogging model is used for further fusing and decoding the fused features to obtain intermediate estimation parameters of the network; and reconstructing the network intermediate estimation parameter and an original foggy image input by the network by using a physical recovery module to obtain a fogless image. According to the method, the local features and the global features can be fused</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115063304A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Pyramid neural network image defogging method and system based on end-to-end multi-size fusion |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T23%3A54%3A17IST&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=CAI%20RONGHUI&rft.date=2022-09-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115063304A%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 |