Low-light image enhancement method for extracting and fusing local and global features
The invention discloses a low-light image enhancement method for extracting and fusing local and global features, and relates to the technical field of image processing. According to the method, a built BrigtFormer network structure is utilized, cross convolution and a self-attention mechanism are o...
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 | YANG WENMING JIANG LIJUN WANG YONG YUAN XINLIN LI BO |
| description | The invention discloses a low-light image enhancement method for extracting and fusing local and global features, and relates to the technical field of image processing. According to the method, a built BrigtFormer network structure is utilized, cross convolution and a self-attention mechanism are organically unified, two advantages of local extraction and global dependence are considered at the same time, features are fused from two dimensions of space and channel by utilizing a feature equalization fusion unit, and the method comprises the following steps. According to the method, the local and global features of the image are extracted and fused at the same time, a new low-illumination image enhancement network model is established, the model fully combines local details and global information learned by the convolution and self-attention module to effectively enhance the low-illumination image, and through a new local-global feature fusion module, the low-illumination image can be effectively enhanced. Th |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114972134A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114972134A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114972134A3</originalsourceid><addsrcrecordid>eNqNik0KwjAUBrNxIeod4gG6iC2ISymKC3Elbsszfk0C-SnJK3p8q3gAVzMMMxe3c3pW3hnL0gUykIiWokZAZBnANj1kn7LEizNpdtFIilMay0d90uS_wfh0n7QH8ZhRlmLWky9Y_bgQ6-Ph2p4qDKlDGUgjgrv2olSz225U3ezrf543CXg5aw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Low-light image enhancement method for extracting and fusing local and global features</title><source>esp@cenet</source><creator>YANG WENMING ; JIANG LIJUN ; WANG YONG ; YUAN XINLIN ; LI BO</creator><creatorcontrib>YANG WENMING ; JIANG LIJUN ; WANG YONG ; YUAN XINLIN ; LI BO</creatorcontrib><description>The invention discloses a low-light image enhancement method for extracting and fusing local and global features, and relates to the technical field of image processing. According to the method, a built BrigtFormer network structure is utilized, cross convolution and a self-attention mechanism are organically unified, two advantages of local extraction and global dependence are considered at the same time, features are fused from two dimensions of space and channel by utilizing a feature equalization fusion unit, and the method comprises the following steps. According to the method, the local and global features of the image are extracted and fused at the same time, a new low-illumination image enhancement network model is established, the model fully combines local details and global information learned by the convolution and self-attention module to effectively enhance the low-illumination image, and through a new local-global feature fusion module, the low-illumination image can be effectively enhanced. Th</description><language>chi ; eng</language><subject>CALCULATING ; 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=20220830&DB=EPODOC&CC=CN&NR=114972134A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76418</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220830&DB=EPODOC&CC=CN&NR=114972134A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YANG WENMING</creatorcontrib><creatorcontrib>JIANG LIJUN</creatorcontrib><creatorcontrib>WANG YONG</creatorcontrib><creatorcontrib>YUAN XINLIN</creatorcontrib><creatorcontrib>LI BO</creatorcontrib><title>Low-light image enhancement method for extracting and fusing local and global features</title><description>The invention discloses a low-light image enhancement method for extracting and fusing local and global features, and relates to the technical field of image processing. According to the method, a built BrigtFormer network structure is utilized, cross convolution and a self-attention mechanism are organically unified, two advantages of local extraction and global dependence are considered at the same time, features are fused from two dimensions of space and channel by utilizing a feature equalization fusion unit, and the method comprises the following steps. According to the method, the local and global features of the image are extracted and fused at the same time, a new low-illumination image enhancement network model is established, the model fully combines local details and global information learned by the convolution and self-attention module to effectively enhance the low-illumination image, and through a new local-global feature fusion module, the low-illumination image can be effectively enhanced. Th</description><subject>CALCULATING</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>eNqNik0KwjAUBrNxIeod4gG6iC2ISymKC3Elbsszfk0C-SnJK3p8q3gAVzMMMxe3c3pW3hnL0gUykIiWokZAZBnANj1kn7LEizNpdtFIilMay0d90uS_wfh0n7QH8ZhRlmLWky9Y_bgQ6-Ph2p4qDKlDGUgjgrv2olSz225U3ezrf543CXg5aw</recordid><startdate>20220830</startdate><enddate>20220830</enddate><creator>YANG WENMING</creator><creator>JIANG LIJUN</creator><creator>WANG YONG</creator><creator>YUAN XINLIN</creator><creator>LI BO</creator><scope>EVB</scope></search><sort><creationdate>20220830</creationdate><title>Low-light image enhancement method for extracting and fusing local and global features</title><author>YANG WENMING ; JIANG LIJUN ; WANG YONG ; YUAN XINLIN ; LI BO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114972134A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>YANG WENMING</creatorcontrib><creatorcontrib>JIANG LIJUN</creatorcontrib><creatorcontrib>WANG YONG</creatorcontrib><creatorcontrib>YUAN XINLIN</creatorcontrib><creatorcontrib>LI BO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YANG WENMING</au><au>JIANG LIJUN</au><au>WANG YONG</au><au>YUAN XINLIN</au><au>LI BO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Low-light image enhancement method for extracting and fusing local and global features</title><date>2022-08-30</date><risdate>2022</risdate><abstract>The invention discloses a low-light image enhancement method for extracting and fusing local and global features, and relates to the technical field of image processing. According to the method, a built BrigtFormer network structure is utilized, cross convolution and a self-attention mechanism are organically unified, two advantages of local extraction and global dependence are considered at the same time, features are fused from two dimensions of space and channel by utilizing a feature equalization fusion unit, and the method comprises the following steps. According to the method, the local and global features of the image are extracted and fused at the same time, a new low-illumination image enhancement network model is established, the model fully combines local details and global information learned by the convolution and self-attention module to effectively enhance the low-illumination image, and through a new local-global feature fusion module, the low-illumination image can be effectively enhanced. Th</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114972134A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Low-light image enhancement method for extracting and fusing local and global features |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T13%3A43%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=YANG%20WENMING&rft.date=2022-08-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114972134A%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 |