Pig detection method based on transfer learning and multi-source domain fusion
The invention provides a pig detection method based on transfer learning and multi-source domain fusion, relates to the field of animal husbandry artificial intelligence, constructs an intermediate domain through a high-definition adaptive improved generative adversarial network model, migrates the...
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 | FAN SONG LIU YUJIE CHENG WANSHENG LUO MINJIE CAO KANG ZHAO HONGYE NIU YIXING SHI CHUNNI |
| description | The invention provides a pig detection method based on transfer learning and multi-source domain fusion, relates to the field of animal husbandry artificial intelligence, constructs an intermediate domain through a high-definition adaptive improved generative adversarial network model, migrates the intermediate domain to a generative domain, and provides a transfer learning evaluation algorithm. Data pictures and the like of other breeding factories are migrated to a target pig farm to strengthen a training data set, a large number of data sets can be obtained only through a small amount of photo data, the image acquisition cost is greatly saved, convenience is provided for large-scale application of artificial intelligence to small and medium-sized farms, and target detection is carried out through a frame-free model to improve the detection precision. The method can be applied to large-scale farm target identification, target tracking can serve as the basis of behavior identification and image segmentation, |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117373059A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117373059A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117373059A3</originalsourceid><addsrcrecordid>eNqNjEEKwjAQAHvxIOof1gcULEGKRymKp-LBe1mTTQ0km5Ld_N8efICnYWCYbTM-wwyOlKyGzJBIP9nBG4UcrK4FWTwViISFA8-A7CDVqKGVXIslcDlhYPBV1sG-2XiMQocfd83xfnsNj5aWPJEsaIlJp2Hsut705nS-XM0_zRcQGTaW</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Pig detection method based on transfer learning and multi-source domain fusion</title><source>esp@cenet</source><creator>FAN SONG ; LIU YUJIE ; CHENG WANSHENG ; LUO MINJIE ; CAO KANG ; ZHAO HONGYE ; NIU YIXING ; SHI CHUNNI</creator><creatorcontrib>FAN SONG ; LIU YUJIE ; CHENG WANSHENG ; LUO MINJIE ; CAO KANG ; ZHAO HONGYE ; NIU YIXING ; SHI CHUNNI</creatorcontrib><description>The invention provides a pig detection method based on transfer learning and multi-source domain fusion, relates to the field of animal husbandry artificial intelligence, constructs an intermediate domain through a high-definition adaptive improved generative adversarial network model, migrates the intermediate domain to a generative domain, and provides a transfer learning evaluation algorithm. Data pictures and the like of other breeding factories are migrated to a target pig farm to strengthen a training data set, a large number of data sets can be obtained only through a small amount of photo data, the image acquisition cost is greatly saved, convenience is provided for large-scale application of artificial intelligence to small and medium-sized farms, and target detection is carried out through a frame-free model to improve the detection precision. The method can be applied to large-scale farm target identification, target tracking can serve as the basis of behavior identification and image segmentation,</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=20240109&DB=EPODOC&CC=CN&NR=117373059A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76419</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240109&DB=EPODOC&CC=CN&NR=117373059A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>FAN SONG</creatorcontrib><creatorcontrib>LIU YUJIE</creatorcontrib><creatorcontrib>CHENG WANSHENG</creatorcontrib><creatorcontrib>LUO MINJIE</creatorcontrib><creatorcontrib>CAO KANG</creatorcontrib><creatorcontrib>ZHAO HONGYE</creatorcontrib><creatorcontrib>NIU YIXING</creatorcontrib><creatorcontrib>SHI CHUNNI</creatorcontrib><title>Pig detection method based on transfer learning and multi-source domain fusion</title><description>The invention provides a pig detection method based on transfer learning and multi-source domain fusion, relates to the field of animal husbandry artificial intelligence, constructs an intermediate domain through a high-definition adaptive improved generative adversarial network model, migrates the intermediate domain to a generative domain, and provides a transfer learning evaluation algorithm. Data pictures and the like of other breeding factories are migrated to a target pig farm to strengthen a training data set, a large number of data sets can be obtained only through a small amount of photo data, the image acquisition cost is greatly saved, convenience is provided for large-scale application of artificial intelligence to small and medium-sized farms, and target detection is carried out through a frame-free model to improve the detection precision. The method can be applied to large-scale farm target identification, target tracking can serve as the basis of behavior identification and image segmentation,</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>eNqNjEEKwjAQAHvxIOof1gcULEGKRymKp-LBe1mTTQ0km5Ld_N8efICnYWCYbTM-wwyOlKyGzJBIP9nBG4UcrK4FWTwViISFA8-A7CDVqKGVXIslcDlhYPBV1sG-2XiMQocfd83xfnsNj5aWPJEsaIlJp2Hsut705nS-XM0_zRcQGTaW</recordid><startdate>20240109</startdate><enddate>20240109</enddate><creator>FAN SONG</creator><creator>LIU YUJIE</creator><creator>CHENG WANSHENG</creator><creator>LUO MINJIE</creator><creator>CAO KANG</creator><creator>ZHAO HONGYE</creator><creator>NIU YIXING</creator><creator>SHI CHUNNI</creator><scope>EVB</scope></search><sort><creationdate>20240109</creationdate><title>Pig detection method based on transfer learning and multi-source domain fusion</title><author>FAN SONG ; LIU YUJIE ; CHENG WANSHENG ; LUO MINJIE ; CAO KANG ; ZHAO HONGYE ; NIU YIXING ; SHI CHUNNI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117373059A3</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>FAN SONG</creatorcontrib><creatorcontrib>LIU YUJIE</creatorcontrib><creatorcontrib>CHENG WANSHENG</creatorcontrib><creatorcontrib>LUO MINJIE</creatorcontrib><creatorcontrib>CAO KANG</creatorcontrib><creatorcontrib>ZHAO HONGYE</creatorcontrib><creatorcontrib>NIU YIXING</creatorcontrib><creatorcontrib>SHI CHUNNI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>FAN SONG</au><au>LIU YUJIE</au><au>CHENG WANSHENG</au><au>LUO MINJIE</au><au>CAO KANG</au><au>ZHAO HONGYE</au><au>NIU YIXING</au><au>SHI CHUNNI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Pig detection method based on transfer learning and multi-source domain fusion</title><date>2024-01-09</date><risdate>2024</risdate><abstract>The invention provides a pig detection method based on transfer learning and multi-source domain fusion, relates to the field of animal husbandry artificial intelligence, constructs an intermediate domain through a high-definition adaptive improved generative adversarial network model, migrates the intermediate domain to a generative domain, and provides a transfer learning evaluation algorithm. Data pictures and the like of other breeding factories are migrated to a target pig farm to strengthen a training data set, a large number of data sets can be obtained only through a small amount of photo data, the image acquisition cost is greatly saved, convenience is provided for large-scale application of artificial intelligence to small and medium-sized farms, and target detection is carried out through a frame-free model to improve the detection precision. The method can be applied to large-scale farm target identification, target tracking can serve as the basis of behavior identification and image segmentation,</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117373059A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Pig detection method based on transfer learning and multi-source domain fusion |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T20%3A51%3A17IST&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=FAN%20SONG&rft.date=2024-01-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117373059A%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 |