Multi-spectral image classification method guided by multiple attention mechanisms
The invention discloses a multi-spectral image classification method guided by multiple attention mechanisms, and the method comprises the steps: firstly carrying out the dimension reduction of an original image through principal component analysis (PCA), segmenting the original image into data bloc...
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 | ZHANG ZHIWEI ZHENG YANG DAI YUNFENG FENG XINGMING BAI JINGJING |
description | The invention discloses a multi-spectral image classification method guided by multiple attention mechanisms, and the method comprises the steps: firstly carrying out the dimension reduction of an original image through principal component analysis (PCA), segmenting the original image into data blocks, enabling an output result to pass through three feature modules, optimizing a three-dimensional convolutional neural network through the attention mechanisms, extracting the spatial spectrum features, inputting the spatial spectrum features into a gated loop (GRU) unit, and carrying out the recognition of the spatial spectrum features. The output size is adjusted through a full-connection neural network, high-layer feature information and low-layer feature information are effectively fused, finally, output data of a feature module and the output data of the recurrent neural network are merged and input into a Softmax layer for classification, and a final classification result is obtained. According to the metho |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117636006A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117636006A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117636006A3</originalsourceid><addsrcrecordid>eNqNyz0KwkAQQOFtLES9w3iAQEJgrSVEbLQQ-zDuTpKB_cOZFN5ehBzA6jXf25rHbQnKlRRy-sYAHHEicAFFeGSHyjlBJJ2zh2lhTx5eH4i_qQQCVKW0GjdjYomyN5sRg9Bh7c4cL_2zu1ZU8kBS0FEiHbp705xsa-vantt_zBd2HTjS</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Multi-spectral image classification method guided by multiple attention mechanisms</title><source>esp@cenet</source><creator>ZHANG ZHIWEI ; ZHENG YANG ; DAI YUNFENG ; FENG XINGMING ; BAI JINGJING</creator><creatorcontrib>ZHANG ZHIWEI ; ZHENG YANG ; DAI YUNFENG ; FENG XINGMING ; BAI JINGJING</creatorcontrib><description>The invention discloses a multi-spectral image classification method guided by multiple attention mechanisms, and the method comprises the steps: firstly carrying out the dimension reduction of an original image through principal component analysis (PCA), segmenting the original image into data blocks, enabling an output result to pass through three feature modules, optimizing a three-dimensional convolutional neural network through the attention mechanisms, extracting the spatial spectrum features, inputting the spatial spectrum features into a gated loop (GRU) unit, and carrying out the recognition of the spatial spectrum features. The output size is adjusted through a full-connection neural network, high-layer feature information and low-layer feature information are effectively fused, finally, output data of a feature module and the output data of the recurrent neural network are merged and input into a Softmax layer for classification, and a final classification result is obtained. According to the metho</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>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&date=20240301&DB=EPODOC&CC=CN&NR=117636006A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25547,76298</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240301&DB=EPODOC&CC=CN&NR=117636006A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG ZHIWEI</creatorcontrib><creatorcontrib>ZHENG YANG</creatorcontrib><creatorcontrib>DAI YUNFENG</creatorcontrib><creatorcontrib>FENG XINGMING</creatorcontrib><creatorcontrib>BAI JINGJING</creatorcontrib><title>Multi-spectral image classification method guided by multiple attention mechanisms</title><description>The invention discloses a multi-spectral image classification method guided by multiple attention mechanisms, and the method comprises the steps: firstly carrying out the dimension reduction of an original image through principal component analysis (PCA), segmenting the original image into data blocks, enabling an output result to pass through three feature modules, optimizing a three-dimensional convolutional neural network through the attention mechanisms, extracting the spatial spectrum features, inputting the spatial spectrum features into a gated loop (GRU) unit, and carrying out the recognition of the spatial spectrum features. The output size is adjusted through a full-connection neural network, high-layer feature information and low-layer feature information are effectively fused, finally, output data of a feature module and the output data of the recurrent neural network are merged and input into a Softmax layer for classification, and a final classification result is obtained. According to the metho</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyz0KwkAQQOFtLES9w3iAQEJgrSVEbLQQ-zDuTpKB_cOZFN5ehBzA6jXf25rHbQnKlRRy-sYAHHEicAFFeGSHyjlBJJ2zh2lhTx5eH4i_qQQCVKW0GjdjYomyN5sRg9Bh7c4cL_2zu1ZU8kBS0FEiHbp705xsa-vantt_zBd2HTjS</recordid><startdate>20240301</startdate><enddate>20240301</enddate><creator>ZHANG ZHIWEI</creator><creator>ZHENG YANG</creator><creator>DAI YUNFENG</creator><creator>FENG XINGMING</creator><creator>BAI JINGJING</creator><scope>EVB</scope></search><sort><creationdate>20240301</creationdate><title>Multi-spectral image classification method guided by multiple attention mechanisms</title><author>ZHANG ZHIWEI ; ZHENG YANG ; DAI YUNFENG ; FENG XINGMING ; BAI JINGJING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117636006A3</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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHANG ZHIWEI</creatorcontrib><creatorcontrib>ZHENG YANG</creatorcontrib><creatorcontrib>DAI YUNFENG</creatorcontrib><creatorcontrib>FENG XINGMING</creatorcontrib><creatorcontrib>BAI JINGJING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG ZHIWEI</au><au>ZHENG YANG</au><au>DAI YUNFENG</au><au>FENG XINGMING</au><au>BAI JINGJING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Multi-spectral image classification method guided by multiple attention mechanisms</title><date>2024-03-01</date><risdate>2024</risdate><abstract>The invention discloses a multi-spectral image classification method guided by multiple attention mechanisms, and the method comprises the steps: firstly carrying out the dimension reduction of an original image through principal component analysis (PCA), segmenting the original image into data blocks, enabling an output result to pass through three feature modules, optimizing a three-dimensional convolutional neural network through the attention mechanisms, extracting the spatial spectrum features, inputting the spatial spectrum features into a gated loop (GRU) unit, and carrying out the recognition of the spatial spectrum features. The output size is adjusted through a full-connection neural network, high-layer feature information and low-layer feature information are effectively fused, finally, output data of a feature module and the output data of the recurrent neural network are merged and input into a Softmax layer for classification, and a final classification result is obtained. According to the metho</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN117636006A |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
title | Multi-spectral image classification method guided by multiple attention mechanisms |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T06%3A15%3A16IST&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=ZHANG%20ZHIWEI&rft.date=2024-03-01&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117636006A%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 |