JOINT-BASED ITEM RECOGNITION
For an input image of a person, a set of object proposals are generated in the form of bounding boxes. A pose detector identifies coordinates in the image corresponding to locations on the person's body, such as the waist, head, hands, and feet of the person. A convolutional neural network rece...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Patent |
| Sprache: | 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 | Hara, Kota Piramuthu, Robinson Jagadeesh, Vignesh |
| description | For an input image of a person, a set of object proposals are generated in the form of bounding boxes. A pose detector identifies coordinates in the image corresponding to locations on the person's body, such as the waist, head, hands, and feet of the person. A convolutional neural network receives the portions of the input image defined by the bounding boxes and generates a feature vector for each image portion. The feature vectors are input to one or more support vector machine classifiers, which generate an output representing a probability of a match with an item. The distance between the bounding box and a joint associated with the item is used to modify the probability. The modified probabilities for the support vector machine are then compared with a threshold and each other to identify the item. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2021406960A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2021406960A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2021406960A13</originalsourceid><addsrcrecordid>eNrjZJDx8vf0C9F1cgx2dVHwDHH1VQhydfZ39_MM8fT342FgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGhiYGZpZmBo6GxsSpAgDxkiGz</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>JOINT-BASED ITEM RECOGNITION</title><source>esp@cenet</source><creator>Hara, Kota ; Piramuthu, Robinson ; Jagadeesh, Vignesh</creator><creatorcontrib>Hara, Kota ; Piramuthu, Robinson ; Jagadeesh, Vignesh</creatorcontrib><description>For an input image of a person, a set of object proposals are generated in the form of bounding boxes. A pose detector identifies coordinates in the image corresponding to locations on the person's body, such as the waist, head, hands, and feet of the person. A convolutional neural network receives the portions of the input image defined by the bounding boxes and generates a feature vector for each image portion. The feature vectors are input to one or more support vector machine classifiers, which generate an output representing a probability of a match with an item. The distance between the bounding box and a joint associated with the item is used to modify the probability. The modified probabilities for the support vector machine are then compared with a threshold and each other to identify the item.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR</subject><creationdate>2021</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=20211230&DB=EPODOC&CC=US&NR=2021406960A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211230&DB=EPODOC&CC=US&NR=2021406960A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Hara, Kota</creatorcontrib><creatorcontrib>Piramuthu, Robinson</creatorcontrib><creatorcontrib>Jagadeesh, Vignesh</creatorcontrib><title>JOINT-BASED ITEM RECOGNITION</title><description>For an input image of a person, a set of object proposals are generated in the form of bounding boxes. A pose detector identifies coordinates in the image corresponding to locations on the person's body, such as the waist, head, hands, and feet of the person. A convolutional neural network receives the portions of the input image defined by the bounding boxes and generates a feature vector for each image portion. The feature vectors are input to one or more support vector machine classifiers, which generate an output representing a probability of a match with an item. The distance between the bounding box and a joint associated with the item is used to modify the probability. The modified probabilities for the support vector machine are then compared with a threshold and each other to identify the item.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZJDx8vf0C9F1cgx2dVHwDHH1VQhydfZ39_MM8fT342FgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGhiYGZpZmBo6GxsSpAgDxkiGz</recordid><startdate>20211230</startdate><enddate>20211230</enddate><creator>Hara, Kota</creator><creator>Piramuthu, Robinson</creator><creator>Jagadeesh, Vignesh</creator><scope>EVB</scope></search><sort><creationdate>20211230</creationdate><title>JOINT-BASED ITEM RECOGNITION</title><author>Hara, Kota ; Piramuthu, Robinson ; Jagadeesh, Vignesh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2021406960A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR</topic><toplevel>online_resources</toplevel><creatorcontrib>Hara, Kota</creatorcontrib><creatorcontrib>Piramuthu, Robinson</creatorcontrib><creatorcontrib>Jagadeesh, Vignesh</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hara, Kota</au><au>Piramuthu, Robinson</au><au>Jagadeesh, Vignesh</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>JOINT-BASED ITEM RECOGNITION</title><date>2021-12-30</date><risdate>2021</risdate><abstract>For an input image of a person, a set of object proposals are generated in the form of bounding boxes. A pose detector identifies coordinates in the image corresponding to locations on the person's body, such as the waist, head, hands, and feet of the person. A convolutional neural network receives the portions of the input image defined by the bounding boxes and generates a feature vector for each image portion. The feature vectors are input to one or more support vector machine classifiers, which generate an output representing a probability of a match with an item. The distance between the bounding box and a joint associated with the item is used to modify the probability. The modified probabilities for the support vector machine are then compared with a threshold and each other to identify the item.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2021406960A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR |
| title | JOINT-BASED ITEM RECOGNITION |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T01%3A29%3A55IST&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=Hara,%20Kota&rft.date=2021-12-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2021406960A1%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 |