Pixel-level classification method, device and equipment and storage medium
The invention discloses a pixel-level classification method, device and equipment and a storage medium. The method comprises: inputting an original picture into an encoder, and obtaining a down-sampling feature map, wherein the size of the down-sampling feature map is 1/2N of the size of the origina...
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 | WANG JUNDONG LIANG DEPENG LIANG ZHUJIN ZHANG ZHUANGHUI ZHANG SHUYE |
| description | The invention discloses a pixel-level classification method, device and equipment and a storage medium. The method comprises: inputting an original picture into an encoder, and obtaining a down-sampling feature map, wherein the size of the down-sampling feature map is 1/2N of the size of the original picture, and N is larger than or equal to 1 and smaller than or equal to 3; inputting the down-sampling feature map into a decoder to obtain an up-sampling feature map, wherein the size of the up-sampling feature map is the same as the size of the original picture; and inputting the up-sampling feature map into a classifier to obtain the classification of each pixel in the original picture. According to the embodiment of the invention, the encoder reduces the original picture to obtain the down-sampling feature map, and the decoder restores the size of the down-sampling feature map to the size of the original picture, so that the classification of each pixel in the original picture can bedetermined subsequently a |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN111382759A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN111382759A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN111382759A3</originalsourceid><addsrcrecordid>eNrjZPAKyKxIzdHNSS1LzVFIzkksLs5My0xOLMnMz1PITS3JyE_RUUhJLctMTlVIzEtRSC0szSzITc0rAfOKS_KLEtNTgQpTMktzeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaGhsYWRuamlozExagAnFjUf</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Pixel-level classification method, device and equipment and storage medium</title><source>esp@cenet</source><creator>WANG JUNDONG ; LIANG DEPENG ; LIANG ZHUJIN ; ZHANG ZHUANGHUI ; ZHANG SHUYE</creator><creatorcontrib>WANG JUNDONG ; LIANG DEPENG ; LIANG ZHUJIN ; ZHANG ZHUANGHUI ; ZHANG SHUYE</creatorcontrib><description>The invention discloses a pixel-level classification method, device and equipment and a storage medium. The method comprises: inputting an original picture into an encoder, and obtaining a down-sampling feature map, wherein the size of the down-sampling feature map is 1/2N of the size of the original picture, and N is larger than or equal to 1 and smaller than or equal to 3; inputting the down-sampling feature map into a decoder to obtain an up-sampling feature map, wherein the size of the up-sampling feature map is the same as the size of the original picture; and inputting the up-sampling feature map into a classifier to obtain the classification of each pixel in the original picture. According to the embodiment of the invention, the encoder reduces the original picture to obtain the down-sampling feature map, and the decoder restores the size of the down-sampling feature map to the size of the original picture, so that the classification of each pixel in the original picture can bedetermined subsequently a</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2020</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=20200707&DB=EPODOC&CC=CN&NR=111382759A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200707&DB=EPODOC&CC=CN&NR=111382759A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG JUNDONG</creatorcontrib><creatorcontrib>LIANG DEPENG</creatorcontrib><creatorcontrib>LIANG ZHUJIN</creatorcontrib><creatorcontrib>ZHANG ZHUANGHUI</creatorcontrib><creatorcontrib>ZHANG SHUYE</creatorcontrib><title>Pixel-level classification method, device and equipment and storage medium</title><description>The invention discloses a pixel-level classification method, device and equipment and a storage medium. The method comprises: inputting an original picture into an encoder, and obtaining a down-sampling feature map, wherein the size of the down-sampling feature map is 1/2N of the size of the original picture, and N is larger than or equal to 1 and smaller than or equal to 3; inputting the down-sampling feature map into a decoder to obtain an up-sampling feature map, wherein the size of the up-sampling feature map is the same as the size of the original picture; and inputting the up-sampling feature map into a classifier to obtain the classification of each pixel in the original picture. According to the embodiment of the invention, the encoder reduces the original picture to obtain the down-sampling feature map, and the decoder restores the size of the down-sampling feature map to the size of the original picture, so that the classification of each pixel in the original picture can bedetermined subsequently a</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPAKyKxIzdHNSS1LzVFIzkksLs5My0xOLMnMz1PITS3JyE_RUUhJLctMTlVIzEtRSC0szSzITc0rAfOKS_KLEtNTgQpTMktzeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaGhsYWRuamlozExagAnFjUf</recordid><startdate>20200707</startdate><enddate>20200707</enddate><creator>WANG JUNDONG</creator><creator>LIANG DEPENG</creator><creator>LIANG ZHUJIN</creator><creator>ZHANG ZHUANGHUI</creator><creator>ZHANG SHUYE</creator><scope>EVB</scope></search><sort><creationdate>20200707</creationdate><title>Pixel-level classification method, device and equipment and storage medium</title><author>WANG JUNDONG ; LIANG DEPENG ; LIANG ZHUJIN ; ZHANG ZHUANGHUI ; ZHANG SHUYE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN111382759A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG JUNDONG</creatorcontrib><creatorcontrib>LIANG DEPENG</creatorcontrib><creatorcontrib>LIANG ZHUJIN</creatorcontrib><creatorcontrib>ZHANG ZHUANGHUI</creatorcontrib><creatorcontrib>ZHANG SHUYE</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG JUNDONG</au><au>LIANG DEPENG</au><au>LIANG ZHUJIN</au><au>ZHANG ZHUANGHUI</au><au>ZHANG SHUYE</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Pixel-level classification method, device and equipment and storage medium</title><date>2020-07-07</date><risdate>2020</risdate><abstract>The invention discloses a pixel-level classification method, device and equipment and a storage medium. The method comprises: inputting an original picture into an encoder, and obtaining a down-sampling feature map, wherein the size of the down-sampling feature map is 1/2N of the size of the original picture, and N is larger than or equal to 1 and smaller than or equal to 3; inputting the down-sampling feature map into a decoder to obtain an up-sampling feature map, wherein the size of the up-sampling feature map is the same as the size of the original picture; and inputting the up-sampling feature map into a classifier to obtain the classification of each pixel in the original picture. According to the embodiment of the invention, the encoder reduces the original picture to obtain the down-sampling feature map, and the decoder restores the size of the down-sampling feature map to the size of the original picture, so that the classification of each pixel in the original picture can bedetermined subsequently a</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN111382759A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Pixel-level classification method, device and equipment and storage medium |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T10%3A45%3A55IST&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%20JUNDONG&rft.date=2020-07-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN111382759A%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 |