Moving target anomaly detection method for fusing image super-resolution reconstruction
The invention provides a moving target anomaly detection method for fusing image super-resolution reconstruction, and relates to the technical field of computer vision. The method comprises the steps of obtaining to-be-detected first image data, inputting the first image data into a pre-constructed...
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 GUANGFU LI HEPING ZHANG XIAOYU CHENG JIAN MI LIFEI |
| description | The invention provides a moving target anomaly detection method for fusing image super-resolution reconstruction, and relates to the technical field of computer vision. The method comprises the steps of obtaining to-be-detected first image data, inputting the first image data into a pre-constructed image super-resolution reconstruction network to obtain second image data after resolution enhancement, performing feature extraction on the second image data to obtain first feature map data corresponding to the second image data, and obtaining a second feature map data corresponding to the second image data; and determining first difference graph data between the first feature graph data and the reference feature graph data, and determining an abnormal region in the first image data according to the first difference graph data and the first feature graph data. Therefore, the interference of noise in the image during anomaly detection can be reduced, the robustness of anomaly detection is improved, and the accurac |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118212696A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118212696A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118212696A3</originalsourceid><addsrcrecordid>eNqNy7EKwjAURuEuDqK-w_UBOqRC0VGK4qKT4FhC-icWmtyQ3Ai-vVh8AKezfGdZPa78GoMj0clBSAf2enrTAIGRkQN5yJMHspzIlvylo9cOlEtEqhMyT2WGCYZDllTmb10trJ4yNr-uqu35dO8uNSL3yFEbBEjf3ZTaN6ppD-1x94_5ANy_OxY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Moving target anomaly detection method for fusing image super-resolution reconstruction</title><source>esp@cenet</source><creator>WANG GUANGFU ; LI HEPING ; ZHANG XIAOYU ; CHENG JIAN ; MI LIFEI</creator><creatorcontrib>WANG GUANGFU ; LI HEPING ; ZHANG XIAOYU ; CHENG JIAN ; MI LIFEI</creatorcontrib><description>The invention provides a moving target anomaly detection method for fusing image super-resolution reconstruction, and relates to the technical field of computer vision. The method comprises the steps of obtaining to-be-detected first image data, inputting the first image data into a pre-constructed image super-resolution reconstruction network to obtain second image data after resolution enhancement, performing feature extraction on the second image data to obtain first feature map data corresponding to the second image data, and obtaining a second feature map data corresponding to the second image data; and determining first difference graph data between the first feature graph data and the reference feature graph data, and determining an abnormal region in the first image data according to the first difference graph data and the first feature graph data. Therefore, the interference of noise in the image during anomaly detection can be reduced, the robustness of anomaly detection is improved, and the accurac</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=20240618&DB=EPODOC&CC=CN&NR=118212696A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240618&DB=EPODOC&CC=CN&NR=118212696A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG GUANGFU</creatorcontrib><creatorcontrib>LI HEPING</creatorcontrib><creatorcontrib>ZHANG XIAOYU</creatorcontrib><creatorcontrib>CHENG JIAN</creatorcontrib><creatorcontrib>MI LIFEI</creatorcontrib><title>Moving target anomaly detection method for fusing image super-resolution reconstruction</title><description>The invention provides a moving target anomaly detection method for fusing image super-resolution reconstruction, and relates to the technical field of computer vision. The method comprises the steps of obtaining to-be-detected first image data, inputting the first image data into a pre-constructed image super-resolution reconstruction network to obtain second image data after resolution enhancement, performing feature extraction on the second image data to obtain first feature map data corresponding to the second image data, and obtaining a second feature map data corresponding to the second image data; and determining first difference graph data between the first feature graph data and the reference feature graph data, and determining an abnormal region in the first image data according to the first difference graph data and the first feature graph data. Therefore, the interference of noise in the image during anomaly detection can be reduced, the robustness of anomaly detection is improved, and the accurac</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>eNqNy7EKwjAURuEuDqK-w_UBOqRC0VGK4qKT4FhC-icWmtyQ3Ai-vVh8AKezfGdZPa78GoMj0clBSAf2enrTAIGRkQN5yJMHspzIlvylo9cOlEtEqhMyT2WGCYZDllTmb10trJ4yNr-uqu35dO8uNSL3yFEbBEjf3ZTaN6ppD-1x94_5ANy_OxY</recordid><startdate>20240618</startdate><enddate>20240618</enddate><creator>WANG GUANGFU</creator><creator>LI HEPING</creator><creator>ZHANG XIAOYU</creator><creator>CHENG JIAN</creator><creator>MI LIFEI</creator><scope>EVB</scope></search><sort><creationdate>20240618</creationdate><title>Moving target anomaly detection method for fusing image super-resolution reconstruction</title><author>WANG GUANGFU ; LI HEPING ; ZHANG XIAOYU ; CHENG JIAN ; MI LIFEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118212696A3</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>WANG GUANGFU</creatorcontrib><creatorcontrib>LI HEPING</creatorcontrib><creatorcontrib>ZHANG XIAOYU</creatorcontrib><creatorcontrib>CHENG JIAN</creatorcontrib><creatorcontrib>MI LIFEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG GUANGFU</au><au>LI HEPING</au><au>ZHANG XIAOYU</au><au>CHENG JIAN</au><au>MI LIFEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Moving target anomaly detection method for fusing image super-resolution reconstruction</title><date>2024-06-18</date><risdate>2024</risdate><abstract>The invention provides a moving target anomaly detection method for fusing image super-resolution reconstruction, and relates to the technical field of computer vision. The method comprises the steps of obtaining to-be-detected first image data, inputting the first image data into a pre-constructed image super-resolution reconstruction network to obtain second image data after resolution enhancement, performing feature extraction on the second image data to obtain first feature map data corresponding to the second image data, and obtaining a second feature map data corresponding to the second image data; and determining first difference graph data between the first feature graph data and the reference feature graph data, and determining an abnormal region in the first image data according to the first difference graph data and the first feature graph data. Therefore, the interference of noise in the image during anomaly detection can be reduced, the robustness of anomaly detection is improved, and the accurac</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118212696A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Moving target anomaly detection method for fusing image super-resolution reconstruction |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T08%3A25%3A40IST&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%20GUANGFU&rft.date=2024-06-18&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118212696A%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 |