Traffic sign detection method and device based on multi-feature fusion and storage medium
The invention discloses a traffic sign detection method and device based on multi-feature fusion, and a storage medium. The method comprises the steps of obtaining a to-be-detected image of a traffic sign; performing color feature extraction and shape feature extraction on the to-be-detected image t...
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 | CHEN DEHUA CHEN XIN DONG XINCI HUANG LI SHU XUANCAI OU YUANXI XU QINMEI XU HAOYI DENG CHEN LIU YUN RAN GUANGWEI |
| description | The invention discloses a traffic sign detection method and device based on multi-feature fusion, and a storage medium. The method comprises the steps of obtaining a to-be-detected image of a traffic sign; performing color feature extraction and shape feature extraction on the to-be-detected image to obtain a first detection image based on color features and shape features; inputting the first detection image into a preset depth feature extraction model to obtain a depth feature-based second detection image output by the depth feature extraction model; wherein the depth feature extraction model is an improved convolutional neural network model LeNet-5; and inputting the first detection image and the second detection image into a preset traffic sign detection model to obtain a traffic sign detection result output by the traffic sign detection model. According to the invention, the most important color features and shape features in the traffic sign image and the depth features extracted through the neural netw |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116052129A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116052129A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116052129A3</originalsourceid><addsrcrecordid>eNqNy0EKwjAUBNBsXIh6h-8BCrai4FKK4spVN67KN5m0gTYpzY_ntwEP4Gpg5s1avZqZrXWaous8GQi0uOBphPTBEHuzlB-nQW-OMJSnNIgrLFjSDLIpZp9hlDBzh-VrXBq3amV5iNj9cqP291tTPwpMoUWcWMND2vpZlufDqSqry_X4j_kCvdg6Zg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Traffic sign detection method and device based on multi-feature fusion and storage medium</title><source>esp@cenet</source><creator>CHEN DEHUA ; CHEN XIN ; DONG XINCI ; HUANG LI ; SHU XUANCAI ; OU YUANXI ; XU QINMEI ; XU HAOYI ; DENG CHEN ; LIU YUN ; RAN GUANGWEI</creator><creatorcontrib>CHEN DEHUA ; CHEN XIN ; DONG XINCI ; HUANG LI ; SHU XUANCAI ; OU YUANXI ; XU QINMEI ; XU HAOYI ; DENG CHEN ; LIU YUN ; RAN GUANGWEI</creatorcontrib><description>The invention discloses a traffic sign detection method and device based on multi-feature fusion, and a storage medium. The method comprises the steps of obtaining a to-be-detected image of a traffic sign; performing color feature extraction and shape feature extraction on the to-be-detected image to obtain a first detection image based on color features and shape features; inputting the first detection image into a preset depth feature extraction model to obtain a depth feature-based second detection image output by the depth feature extraction model; wherein the depth feature extraction model is an improved convolutional neural network model LeNet-5; and inputting the first detection image and the second detection image into a preset traffic sign detection model to obtain a traffic sign detection result output by the traffic sign detection model. According to the invention, the most important color features and shape features in the traffic sign image and the depth features extracted through the neural netw</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2023</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=20230502&DB=EPODOC&CC=CN&NR=116052129A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25569,76553</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230502&DB=EPODOC&CC=CN&NR=116052129A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN DEHUA</creatorcontrib><creatorcontrib>CHEN XIN</creatorcontrib><creatorcontrib>DONG XINCI</creatorcontrib><creatorcontrib>HUANG LI</creatorcontrib><creatorcontrib>SHU XUANCAI</creatorcontrib><creatorcontrib>OU YUANXI</creatorcontrib><creatorcontrib>XU QINMEI</creatorcontrib><creatorcontrib>XU HAOYI</creatorcontrib><creatorcontrib>DENG CHEN</creatorcontrib><creatorcontrib>LIU YUN</creatorcontrib><creatorcontrib>RAN GUANGWEI</creatorcontrib><title>Traffic sign detection method and device based on multi-feature fusion and storage medium</title><description>The invention discloses a traffic sign detection method and device based on multi-feature fusion, and a storage medium. The method comprises the steps of obtaining a to-be-detected image of a traffic sign; performing color feature extraction and shape feature extraction on the to-be-detected image to obtain a first detection image based on color features and shape features; inputting the first detection image into a preset depth feature extraction model to obtain a depth feature-based second detection image output by the depth feature extraction model; wherein the depth feature extraction model is an improved convolutional neural network model LeNet-5; and inputting the first detection image and the second detection image into a preset traffic sign detection model to obtain a traffic sign detection result output by the traffic sign detection model. According to the invention, the most important color features and shape features in the traffic sign image and the depth features extracted through the neural netw</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNy0EKwjAUBNBsXIh6h-8BCrai4FKK4spVN67KN5m0gTYpzY_ntwEP4Gpg5s1avZqZrXWaous8GQi0uOBphPTBEHuzlB-nQW-OMJSnNIgrLFjSDLIpZp9hlDBzh-VrXBq3amV5iNj9cqP291tTPwpMoUWcWMND2vpZlufDqSqry_X4j_kCvdg6Zg</recordid><startdate>20230502</startdate><enddate>20230502</enddate><creator>CHEN DEHUA</creator><creator>CHEN XIN</creator><creator>DONG XINCI</creator><creator>HUANG LI</creator><creator>SHU XUANCAI</creator><creator>OU YUANXI</creator><creator>XU QINMEI</creator><creator>XU HAOYI</creator><creator>DENG CHEN</creator><creator>LIU YUN</creator><creator>RAN GUANGWEI</creator><scope>EVB</scope></search><sort><creationdate>20230502</creationdate><title>Traffic sign detection method and device based on multi-feature fusion and storage medium</title><author>CHEN DEHUA ; CHEN XIN ; DONG XINCI ; HUANG LI ; SHU XUANCAI ; OU YUANXI ; XU QINMEI ; XU HAOYI ; DENG CHEN ; LIU YUN ; RAN GUANGWEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116052129A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</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>CHEN DEHUA</creatorcontrib><creatorcontrib>CHEN XIN</creatorcontrib><creatorcontrib>DONG XINCI</creatorcontrib><creatorcontrib>HUANG LI</creatorcontrib><creatorcontrib>SHU XUANCAI</creatorcontrib><creatorcontrib>OU YUANXI</creatorcontrib><creatorcontrib>XU QINMEI</creatorcontrib><creatorcontrib>XU HAOYI</creatorcontrib><creatorcontrib>DENG CHEN</creatorcontrib><creatorcontrib>LIU YUN</creatorcontrib><creatorcontrib>RAN GUANGWEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN DEHUA</au><au>CHEN XIN</au><au>DONG XINCI</au><au>HUANG LI</au><au>SHU XUANCAI</au><au>OU YUANXI</au><au>XU QINMEI</au><au>XU HAOYI</au><au>DENG CHEN</au><au>LIU YUN</au><au>RAN GUANGWEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Traffic sign detection method and device based on multi-feature fusion and storage medium</title><date>2023-05-02</date><risdate>2023</risdate><abstract>The invention discloses a traffic sign detection method and device based on multi-feature fusion, and a storage medium. The method comprises the steps of obtaining a to-be-detected image of a traffic sign; performing color feature extraction and shape feature extraction on the to-be-detected image to obtain a first detection image based on color features and shape features; inputting the first detection image into a preset depth feature extraction model to obtain a depth feature-based second detection image output by the depth feature extraction model; wherein the depth feature extraction model is an improved convolutional neural network model LeNet-5; and inputting the first detection image and the second detection image into a preset traffic sign detection model to obtain a traffic sign detection result output by the traffic sign detection model. According to the invention, the most important color features and shape features in the traffic sign image and the depth features extracted through the neural netw</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116052129A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Traffic sign detection method and device based on multi-feature fusion 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=2024-12-09T18%3A47%3A58IST&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%20DEHUA&rft.date=2023-05-02&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116052129A%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 |