Deep learning algorithm-based method for evaluating silting state of artificial fish reef in sonar image
The invention provides a deep learning algorithm-based method for evaluating a silting state of an artificial fish reef in a sonar image, and the method comprises the following steps: 1, data collection: employing a shipborne Ocuus 750d multi-beam imaging sonar to collect sonar images and video data...
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 | SONG YIFAN FAN XIUMEI CUI XUESEN WU ZULI QUAN WEIMIN XIONG MINSI WU YUMEI SHI YONGCHUANG |
| description | The invention provides a deep learning algorithm-based method for evaluating a silting state of an artificial fish reef in a sonar image, and the method comprises the following steps: 1, data collection: employing a shipborne Ocuus 750d multi-beam imaging sonar to collect sonar images and video data of an artificial fish reef region and a surrounding marine environment; 2, data preprocessing, wherein the data are divided into training set pictures, verification set pictures and test set pictures according to the proportion of 8: 1: 1; step 3, feature extraction and analysis: using a deep learning algorithm of a MobileNetV3 improved Yolov8pose detection model to identify the artificial fish reef, extracting and screening key point features of an artificial fish reef cube plane, and determining a feature mode related to the artificial fish reef so as to facilitate subsequent attitude state identification training; and 4, model construction: extracting a water bottom plane and an artificial fish reef silting par |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118262225A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118262225A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118262225A3</originalsourceid><addsrcrecordid>eNqNyjEOwjAMBdAuDAi4gzlAhwaBWKsCYmJir0z701hKkygxnB8hOADTW96ycicgkQfnIGEi9lPMom6uH1ww0gx1cSQbM-HF_sn6WUX8V2UFRUucVawMwp6sFEcZsCSBSgycSWaesK4Wln3B5ueq2l7O9-5aI8UeJfGAAO27W9MczcEYs293_5w37rBAEw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Deep learning algorithm-based method for evaluating silting state of artificial fish reef in sonar image</title><source>esp@cenet</source><creator>SONG YIFAN ; FAN XIUMEI ; CUI XUESEN ; WU ZULI ; QUAN WEIMIN ; XIONG MINSI ; WU YUMEI ; SHI YONGCHUANG</creator><creatorcontrib>SONG YIFAN ; FAN XIUMEI ; CUI XUESEN ; WU ZULI ; QUAN WEIMIN ; XIONG MINSI ; WU YUMEI ; SHI YONGCHUANG</creatorcontrib><description>The invention provides a deep learning algorithm-based method for evaluating a silting state of an artificial fish reef in a sonar image, and the method comprises the following steps: 1, data collection: employing a shipborne Ocuus 750d multi-beam imaging sonar to collect sonar images and video data of an artificial fish reef region and a surrounding marine environment; 2, data preprocessing, wherein the data are divided into training set pictures, verification set pictures and test set pictures according to the proportion of 8: 1: 1; step 3, feature extraction and analysis: using a deep learning algorithm of a MobileNetV3 improved Yolov8pose detection model to identify the artificial fish reef, extracting and screening key point features of an artificial fish reef cube plane, and determining a feature mode related to the artificial fish reef so as to facilitate subsequent attitude state identification training; and 4, model construction: extracting a water bottom plane and an artificial fish reef silting par</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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=20240628&DB=EPODOC&CC=CN&NR=118262225A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240628&DB=EPODOC&CC=CN&NR=118262225A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SONG YIFAN</creatorcontrib><creatorcontrib>FAN XIUMEI</creatorcontrib><creatorcontrib>CUI XUESEN</creatorcontrib><creatorcontrib>WU ZULI</creatorcontrib><creatorcontrib>QUAN WEIMIN</creatorcontrib><creatorcontrib>XIONG MINSI</creatorcontrib><creatorcontrib>WU YUMEI</creatorcontrib><creatorcontrib>SHI YONGCHUANG</creatorcontrib><title>Deep learning algorithm-based method for evaluating silting state of artificial fish reef in sonar image</title><description>The invention provides a deep learning algorithm-based method for evaluating a silting state of an artificial fish reef in a sonar image, and the method comprises the following steps: 1, data collection: employing a shipborne Ocuus 750d multi-beam imaging sonar to collect sonar images and video data of an artificial fish reef region and a surrounding marine environment; 2, data preprocessing, wherein the data are divided into training set pictures, verification set pictures and test set pictures according to the proportion of 8: 1: 1; step 3, feature extraction and analysis: using a deep learning algorithm of a MobileNetV3 improved Yolov8pose detection model to identify the artificial fish reef, extracting and screening key point features of an artificial fish reef cube plane, and determining a feature mode related to the artificial fish reef so as to facilitate subsequent attitude state identification training; and 4, model construction: extracting a water bottom plane and an artificial fish reef silting par</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjEOwjAMBdAuDAi4gzlAhwaBWKsCYmJir0z701hKkygxnB8hOADTW96ycicgkQfnIGEi9lPMom6uH1ww0gx1cSQbM-HF_sn6WUX8V2UFRUucVawMwp6sFEcZsCSBSgycSWaesK4Wln3B5ueq2l7O9-5aI8UeJfGAAO27W9MczcEYs293_5w37rBAEw</recordid><startdate>20240628</startdate><enddate>20240628</enddate><creator>SONG YIFAN</creator><creator>FAN XIUMEI</creator><creator>CUI XUESEN</creator><creator>WU ZULI</creator><creator>QUAN WEIMIN</creator><creator>XIONG MINSI</creator><creator>WU YUMEI</creator><creator>SHI YONGCHUANG</creator><scope>EVB</scope></search><sort><creationdate>20240628</creationdate><title>Deep learning algorithm-based method for evaluating silting state of artificial fish reef in sonar image</title><author>SONG YIFAN ; FAN XIUMEI ; CUI XUESEN ; WU ZULI ; QUAN WEIMIN ; XIONG MINSI ; WU YUMEI ; SHI YONGCHUANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118262225A3</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>SONG YIFAN</creatorcontrib><creatorcontrib>FAN XIUMEI</creatorcontrib><creatorcontrib>CUI XUESEN</creatorcontrib><creatorcontrib>WU ZULI</creatorcontrib><creatorcontrib>QUAN WEIMIN</creatorcontrib><creatorcontrib>XIONG MINSI</creatorcontrib><creatorcontrib>WU YUMEI</creatorcontrib><creatorcontrib>SHI YONGCHUANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SONG YIFAN</au><au>FAN XIUMEI</au><au>CUI XUESEN</au><au>WU ZULI</au><au>QUAN WEIMIN</au><au>XIONG MINSI</au><au>WU YUMEI</au><au>SHI YONGCHUANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Deep learning algorithm-based method for evaluating silting state of artificial fish reef in sonar image</title><date>2024-06-28</date><risdate>2024</risdate><abstract>The invention provides a deep learning algorithm-based method for evaluating a silting state of an artificial fish reef in a sonar image, and the method comprises the following steps: 1, data collection: employing a shipborne Ocuus 750d multi-beam imaging sonar to collect sonar images and video data of an artificial fish reef region and a surrounding marine environment; 2, data preprocessing, wherein the data are divided into training set pictures, verification set pictures and test set pictures according to the proportion of 8: 1: 1; step 3, feature extraction and analysis: using a deep learning algorithm of a MobileNetV3 improved Yolov8pose detection model to identify the artificial fish reef, extracting and screening key point features of an artificial fish reef cube plane, and determining a feature mode related to the artificial fish reef so as to facilitate subsequent attitude state identification training; and 4, model construction: extracting a water bottom plane and an artificial fish reef silting par</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118262225A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Deep learning algorithm-based method for evaluating silting state of artificial fish reef in sonar image |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T13%3A34%3A00IST&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=SONG%20YIFAN&rft.date=2024-06-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118262225A%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 |