Light-weight SSD traffic sign detection algorithm
A traffic sign detection algorithm of a lightweight SSD (Solid State Disk) comprises the following steps: based on an SSD network structure, replacing VGG16 in an SSD network with a MobileNetV3large network, and taking the MobileNetV3large network as a basic feature extraction network to form an MV3...
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 | HE HAO QIN SHENGTAO WEI LAI DU JIAHUI ZHANG GANG DU XUAN YOU JIARUI |
| description | A traffic sign detection algorithm of a lightweight SSD (Solid State Disk) comprises the following steps: based on an SSD network structure, replacing VGG16 in an SSD network with a MobileNetV3large network, and taking the MobileNetV3large network as a basic feature extraction network to form an MV3-SSD network structure; replacing the corresponding standard convolution by using an inverse residual structure Bcheck added with an SE module to serve as an output feature layer of target detection; and performing prediction through the optimized prior frame, and obtaining the position and the category of the traffic sign through a non-maximum suppression algorithm. According to the method, the detection efficiency is greatly improved while the detection precision of the traffic sign is guaranteed, the method is well suitable for embedded terminal equipment, and the requirement of automatic driving for high-quality identification of traffic sign information is met.
一种轻量化SSD的交通标志检测算法，其步骤包括：基于SSD网络结构，采用MobileNetV3_l |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116416598A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116416598A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116416598A3</originalsourceid><addsrcrecordid>eNrjZDD0yUzPKNEtTwVRCsHBLgolRYlpaZnJCsWZ6XkKKaklqcklmfl5Cok56flFmSUZuTwMrGmJOcWpvFCam0HRzTXE2UM3tSA_PrW4IDE5NS-1JN7Zz9DQzMTQzNTSwtGYGDUAbb8rdw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Light-weight SSD traffic sign detection algorithm</title><source>esp@cenet</source><creator>HE HAO ; QIN SHENGTAO ; WEI LAI ; DU JIAHUI ; ZHANG GANG ; DU XUAN ; YOU JIARUI</creator><creatorcontrib>HE HAO ; QIN SHENGTAO ; WEI LAI ; DU JIAHUI ; ZHANG GANG ; DU XUAN ; YOU JIARUI</creatorcontrib><description>A traffic sign detection algorithm of a lightweight SSD (Solid State Disk) comprises the following steps: based on an SSD network structure, replacing VGG16 in an SSD network with a MobileNetV3large network, and taking the MobileNetV3large network as a basic feature extraction network to form an MV3-SSD network structure; replacing the corresponding standard convolution by using an inverse residual structure Bcheck added with an SE module to serve as an output feature layer of target detection; and performing prediction through the optimized prior frame, and obtaining the position and the category of the traffic sign through a non-maximum suppression algorithm. According to the method, the detection efficiency is greatly improved while the detection precision of the traffic sign is guaranteed, the method is well suitable for embedded terminal equipment, and the requirement of automatic driving for high-quality identification of traffic sign information is met.
一种轻量化SSD的交通标志检测算法，其步骤包括：基于SSD网络结构，采用MobileNetV3_l</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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=20230711&DB=EPODOC&CC=CN&NR=116416598A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76294</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230711&DB=EPODOC&CC=CN&NR=116416598A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HE HAO</creatorcontrib><creatorcontrib>QIN SHENGTAO</creatorcontrib><creatorcontrib>WEI LAI</creatorcontrib><creatorcontrib>DU JIAHUI</creatorcontrib><creatorcontrib>ZHANG GANG</creatorcontrib><creatorcontrib>DU XUAN</creatorcontrib><creatorcontrib>YOU JIARUI</creatorcontrib><title>Light-weight SSD traffic sign detection algorithm</title><description>A traffic sign detection algorithm of a lightweight SSD (Solid State Disk) comprises the following steps: based on an SSD network structure, replacing VGG16 in an SSD network with a MobileNetV3large network, and taking the MobileNetV3large network as a basic feature extraction network to form an MV3-SSD network structure; replacing the corresponding standard convolution by using an inverse residual structure Bcheck added with an SE module to serve as an output feature layer of target detection; and performing prediction through the optimized prior frame, and obtaining the position and the category of the traffic sign through a non-maximum suppression algorithm. According to the method, the detection efficiency is greatly improved while the detection precision of the traffic sign is guaranteed, the method is well suitable for embedded terminal equipment, and the requirement of automatic driving for high-quality identification of traffic sign information is met.
一种轻量化SSD的交通标志检测算法，其步骤包括：基于SSD网络结构，采用MobileNetV3_l</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDD0yUzPKNEtTwVRCsHBLgolRYlpaZnJCsWZ6XkKKaklqcklmfl5Cok56flFmSUZuTwMrGmJOcWpvFCam0HRzTXE2UM3tSA_PrW4IDE5NS-1JN7Zz9DQzMTQzNTSwtGYGDUAbb8rdw</recordid><startdate>20230711</startdate><enddate>20230711</enddate><creator>HE HAO</creator><creator>QIN SHENGTAO</creator><creator>WEI LAI</creator><creator>DU JIAHUI</creator><creator>ZHANG GANG</creator><creator>DU XUAN</creator><creator>YOU JIARUI</creator><scope>EVB</scope></search><sort><creationdate>20230711</creationdate><title>Light-weight SSD traffic sign detection algorithm</title><author>HE HAO ; QIN SHENGTAO ; WEI LAI ; DU JIAHUI ; ZHANG GANG ; DU XUAN ; YOU JIARUI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116416598A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>HE HAO</creatorcontrib><creatorcontrib>QIN SHENGTAO</creatorcontrib><creatorcontrib>WEI LAI</creatorcontrib><creatorcontrib>DU JIAHUI</creatorcontrib><creatorcontrib>ZHANG GANG</creatorcontrib><creatorcontrib>DU XUAN</creatorcontrib><creatorcontrib>YOU JIARUI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HE HAO</au><au>QIN SHENGTAO</au><au>WEI LAI</au><au>DU JIAHUI</au><au>ZHANG GANG</au><au>DU XUAN</au><au>YOU JIARUI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Light-weight SSD traffic sign detection algorithm</title><date>2023-07-11</date><risdate>2023</risdate><abstract>A traffic sign detection algorithm of a lightweight SSD (Solid State Disk) comprises the following steps: based on an SSD network structure, replacing VGG16 in an SSD network with a MobileNetV3large network, and taking the MobileNetV3large network as a basic feature extraction network to form an MV3-SSD network structure; replacing the corresponding standard convolution by using an inverse residual structure Bcheck added with an SE module to serve as an output feature layer of target detection; and performing prediction through the optimized prior frame, and obtaining the position and the category of the traffic sign through a non-maximum suppression algorithm. According to the method, the detection efficiency is greatly improved while the detection precision of the traffic sign is guaranteed, the method is well suitable for embedded terminal equipment, and the requirement of automatic driving for high-quality identification of traffic sign information is met.
一种轻量化SSD的交通标志检测算法，其步骤包括：基于SSD网络结构，采用MobileNetV3_l</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116416598A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Light-weight SSD traffic sign detection algorithm |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T06%3A20%3A54IST&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=HE%20HAO&rft.date=2023-07-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116416598A%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 |