Deep learning-based single-target object segmentation method and detection equipment
The invention belongs to the technical field of image processing in motor snap spring groove height detection, and discloses a deep learning-based single-target object segmentation method and detection equipment, and the method comprises the steps: segmenting a complete target through an improved UN...
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 | WANG CHANGKAI LIU ZHICHANG ZHANG YASHENG WANG DONGNIAN XU RUILONG |
| description | The invention belongs to the technical field of image processing in motor snap spring groove height detection, and discloses a deep learning-based single-target object segmentation method and detection equipment, and the method comprises the steps: segmenting a complete target through an improved UNet neural network under the condition that the same type of incomplete target and complete target exist at the same time, and filtering out the complete target. According to the method, the UNet neural network is improved, when the same type of incomplete targets and complete targets exist at the same time, the network can directly segment the complete targets, and the incomplete targets are filtered out. The method is greatly helpful for only considering the condition of the complete target, reduces the interference of the incomplete target, and reduces the segmentation steps of the complete target. Compared with the original UNet network, the improved UNet network has the advantage that the network segmentation e |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN111951270A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN111951270A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN111951270A3</originalsourceid><addsrcrecordid>eNqNijEOwjAQBN1QIOAPxwMsYRBClCiAqKjSR5d4MUaObeLj_yQSD6Ca1ezMVX0GMgXwEH10uuUCS2WcAVp4cBBK7QudUIHrEYXFp0g95JkscbRkIeM9Sbw_Pk_NUs0eHApWPy7U-nqpq5tGTg1K5g4R0lR3Y8xxb7aHzWn3T_MFv3k5MQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Deep learning-based single-target object segmentation method and detection equipment</title><source>esp@cenet</source><creator>WANG CHANGKAI ; LIU ZHICHANG ; ZHANG YASHENG ; WANG DONGNIAN ; XU RUILONG</creator><creatorcontrib>WANG CHANGKAI ; LIU ZHICHANG ; ZHANG YASHENG ; WANG DONGNIAN ; XU RUILONG</creatorcontrib><description>The invention belongs to the technical field of image processing in motor snap spring groove height detection, and discloses a deep learning-based single-target object segmentation method and detection equipment, and the method comprises the steps: segmenting a complete target through an improved UNet neural network under the condition that the same type of incomplete target and complete target exist at the same time, and filtering out the complete target. According to the method, the UNet neural network is improved, when the same type of incomplete targets and complete targets exist at the same time, the network can directly segment the complete targets, and the incomplete targets are filtered out. The method is greatly helpful for only considering the condition of the complete target, reduces the interference of the incomplete target, and reduces the segmentation steps of the complete target. Compared with the original UNet network, the improved UNet network has the advantage that the network segmentation e</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2020</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=20201117&DB=EPODOC&CC=CN&NR=111951270A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201117&DB=EPODOC&CC=CN&NR=111951270A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG CHANGKAI</creatorcontrib><creatorcontrib>LIU ZHICHANG</creatorcontrib><creatorcontrib>ZHANG YASHENG</creatorcontrib><creatorcontrib>WANG DONGNIAN</creatorcontrib><creatorcontrib>XU RUILONG</creatorcontrib><title>Deep learning-based single-target object segmentation method and detection equipment</title><description>The invention belongs to the technical field of image processing in motor snap spring groove height detection, and discloses a deep learning-based single-target object segmentation method and detection equipment, and the method comprises the steps: segmenting a complete target through an improved UNet neural network under the condition that the same type of incomplete target and complete target exist at the same time, and filtering out the complete target. According to the method, the UNet neural network is improved, when the same type of incomplete targets and complete targets exist at the same time, the network can directly segment the complete targets, and the incomplete targets are filtered out. The method is greatly helpful for only considering the condition of the complete target, reduces the interference of the incomplete target, and reduces the segmentation steps of the complete target. Compared with the original UNet network, the improved UNet network has the advantage that the network segmentation e</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNijEOwjAQBN1QIOAPxwMsYRBClCiAqKjSR5d4MUaObeLj_yQSD6Ca1ezMVX0GMgXwEH10uuUCS2WcAVp4cBBK7QudUIHrEYXFp0g95JkscbRkIeM9Sbw_Pk_NUs0eHApWPy7U-nqpq5tGTg1K5g4R0lR3Y8xxb7aHzWn3T_MFv3k5MQ</recordid><startdate>20201117</startdate><enddate>20201117</enddate><creator>WANG CHANGKAI</creator><creator>LIU ZHICHANG</creator><creator>ZHANG YASHENG</creator><creator>WANG DONGNIAN</creator><creator>XU RUILONG</creator><scope>EVB</scope></search><sort><creationdate>20201117</creationdate><title>Deep learning-based single-target object segmentation method and detection equipment</title><author>WANG CHANGKAI ; LIU ZHICHANG ; ZHANG YASHENG ; WANG DONGNIAN ; XU RUILONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN111951270A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG CHANGKAI</creatorcontrib><creatorcontrib>LIU ZHICHANG</creatorcontrib><creatorcontrib>ZHANG YASHENG</creatorcontrib><creatorcontrib>WANG DONGNIAN</creatorcontrib><creatorcontrib>XU RUILONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG CHANGKAI</au><au>LIU ZHICHANG</au><au>ZHANG YASHENG</au><au>WANG DONGNIAN</au><au>XU RUILONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Deep learning-based single-target object segmentation method and detection equipment</title><date>2020-11-17</date><risdate>2020</risdate><abstract>The invention belongs to the technical field of image processing in motor snap spring groove height detection, and discloses a deep learning-based single-target object segmentation method and detection equipment, and the method comprises the steps: segmenting a complete target through an improved UNet neural network under the condition that the same type of incomplete target and complete target exist at the same time, and filtering out the complete target. According to the method, the UNet neural network is improved, when the same type of incomplete targets and complete targets exist at the same time, the network can directly segment the complete targets, and the incomplete targets are filtered out. The method is greatly helpful for only considering the condition of the complete target, reduces the interference of the incomplete target, and reduces the segmentation steps of the complete target. Compared with the original UNet network, the improved UNet network has the advantage that the network segmentation e</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN111951270A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Deep learning-based single-target object segmentation method and detection equipment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T18%3A40%3A45IST&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=WANG%20CHANGKAI&rft.date=2020-11-17&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN111951270A%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 |