Training method of posture detection model and driving method and device of digital human
The invention provides a training method of a posture detection model, a driving method and device of a digital human, and computer equipment. The training method comprises the following steps: acquiring a training image containing a preset object, a first key point coordinate of the preset object a...
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 | LU ZENG ZHAO HANFENG PANG GUOLIANG ZHANG SHUNSI |
| description | The invention provides a training method of a posture detection model, a driving method and device of a digital human, and computer equipment. The training method comprises the following steps: acquiring a training image containing a preset object, a first key point coordinate of the preset object and a key point heat map of the preset object; inputting the training image into an initial posture detection model to obtain a predicted key point coordinate of the preset object by using a coordinate regression module in the initial posture detection model, and obtaining a predicted key point heat map by using a heat map generation module in the initial posture detection model; and training the initial posture detection model to obtain a posture detection model by taking the reduction of the difference between the first key point coordinate and the predicted key point coordinate and the reduction of the difference between the key point heat map and the predicted key point heat map as targets. The training method g |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115331265A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115331265A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115331265A3</originalsourceid><addsrcrecordid>eNqNi7sKwkAQAK-xEPUf1g-wOI_YS4hYWaWxCsvtJlm4F3eXfL8oFpZWA8PMVj37jBIkTOC5zpEgjpBiqUtmIK5sq8QAPhI7wEBAWdaf-qN4FcvvkWSSig7mxWPYq82IrvDhy5063rq-vZ84xYFLQsuB69A-tG6M0edLczX_NC_Nrzpg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Training method of posture detection model and driving method and device of digital human</title><source>esp@cenet</source><creator>LU ZENG ; ZHAO HANFENG ; PANG GUOLIANG ; ZHANG SHUNSI</creator><creatorcontrib>LU ZENG ; ZHAO HANFENG ; PANG GUOLIANG ; ZHANG SHUNSI</creatorcontrib><description>The invention provides a training method of a posture detection model, a driving method and device of a digital human, and computer equipment. The training method comprises the following steps: acquiring a training image containing a preset object, a first key point coordinate of the preset object and a key point heat map of the preset object; inputting the training image into an initial posture detection model to obtain a predicted key point coordinate of the preset object by using a coordinate regression module in the initial posture detection model, and obtaining a predicted key point heat map by using a heat map generation module in the initial posture detection model; and training the initial posture detection model to obtain a posture detection model by taking the reduction of the difference between the first key point coordinate and the predicted key point coordinate and the reduction of the difference between the key point heat map and the predicted key point heat map as targets. The training method g</description><language>chi ; eng</language><subject>AMUSEMENTS ; CALCULATING ; CARD, BOARD, OR ROULETTE GAMES ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; GAMES ; GAMES NOT OTHERWISE PROVIDED FOR ; HUMAN NECESSITIES ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; INDOOR GAMES USING SMALL MOVING PLAYING BODIES ; PHYSICS ; SPORTS ; VIDEO GAMES</subject><creationdate>2022</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=20221111&DB=EPODOC&CC=CN&NR=115331265A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221111&DB=EPODOC&CC=CN&NR=115331265A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LU ZENG</creatorcontrib><creatorcontrib>ZHAO HANFENG</creatorcontrib><creatorcontrib>PANG GUOLIANG</creatorcontrib><creatorcontrib>ZHANG SHUNSI</creatorcontrib><title>Training method of posture detection model and driving method and device of digital human</title><description>The invention provides a training method of a posture detection model, a driving method and device of a digital human, and computer equipment. The training method comprises the following steps: acquiring a training image containing a preset object, a first key point coordinate of the preset object and a key point heat map of the preset object; inputting the training image into an initial posture detection model to obtain a predicted key point coordinate of the preset object by using a coordinate regression module in the initial posture detection model, and obtaining a predicted key point heat map by using a heat map generation module in the initial posture detection model; and training the initial posture detection model to obtain a posture detection model by taking the reduction of the difference between the first key point coordinate and the predicted key point coordinate and the reduction of the difference between the key point heat map and the predicted key point heat map as targets. The training method g</description><subject>AMUSEMENTS</subject><subject>CALCULATING</subject><subject>CARD, BOARD, OR ROULETTE GAMES</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>GAMES</subject><subject>GAMES NOT OTHERWISE PROVIDED FOR</subject><subject>HUMAN NECESSITIES</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>INDOOR GAMES USING SMALL MOVING PLAYING BODIES</subject><subject>PHYSICS</subject><subject>SPORTS</subject><subject>VIDEO GAMES</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi7sKwkAQAK-xEPUf1g-wOI_YS4hYWaWxCsvtJlm4F3eXfL8oFpZWA8PMVj37jBIkTOC5zpEgjpBiqUtmIK5sq8QAPhI7wEBAWdaf-qN4FcvvkWSSig7mxWPYq82IrvDhy5063rq-vZ84xYFLQsuB69A-tG6M0edLczX_NC_Nrzpg</recordid><startdate>20221111</startdate><enddate>20221111</enddate><creator>LU ZENG</creator><creator>ZHAO HANFENG</creator><creator>PANG GUOLIANG</creator><creator>ZHANG SHUNSI</creator><scope>EVB</scope></search><sort><creationdate>20221111</creationdate><title>Training method of posture detection model and driving method and device of digital human</title><author>LU ZENG ; ZHAO HANFENG ; PANG GUOLIANG ; ZHANG SHUNSI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115331265A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>AMUSEMENTS</topic><topic>CALCULATING</topic><topic>CARD, BOARD, OR ROULETTE GAMES</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>GAMES</topic><topic>GAMES NOT OTHERWISE PROVIDED FOR</topic><topic>HUMAN NECESSITIES</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>INDOOR GAMES USING SMALL MOVING PLAYING BODIES</topic><topic>PHYSICS</topic><topic>SPORTS</topic><topic>VIDEO GAMES</topic><toplevel>online_resources</toplevel><creatorcontrib>LU ZENG</creatorcontrib><creatorcontrib>ZHAO HANFENG</creatorcontrib><creatorcontrib>PANG GUOLIANG</creatorcontrib><creatorcontrib>ZHANG SHUNSI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LU ZENG</au><au>ZHAO HANFENG</au><au>PANG GUOLIANG</au><au>ZHANG SHUNSI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Training method of posture detection model and driving method and device of digital human</title><date>2022-11-11</date><risdate>2022</risdate><abstract>The invention provides a training method of a posture detection model, a driving method and device of a digital human, and computer equipment. The training method comprises the following steps: acquiring a training image containing a preset object, a first key point coordinate of the preset object and a key point heat map of the preset object; inputting the training image into an initial posture detection model to obtain a predicted key point coordinate of the preset object by using a coordinate regression module in the initial posture detection model, and obtaining a predicted key point heat map by using a heat map generation module in the initial posture detection model; and training the initial posture detection model to obtain a posture detection model by taking the reduction of the difference between the first key point coordinate and the predicted key point coordinate and the reduction of the difference between the key point heat map and the predicted key point heat map as targets. The training method g</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115331265A |
| source | esp@cenet |
| subjects | AMUSEMENTS CALCULATING CARD, BOARD, OR ROULETTE GAMES COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING GAMES GAMES NOT OTHERWISE PROVIDED FOR HUMAN NECESSITIES IMAGE DATA PROCESSING OR GENERATION, IN GENERAL INDOOR GAMES USING SMALL MOVING PLAYING BODIES PHYSICS SPORTS VIDEO GAMES |
| title | Training method of posture detection model and driving method and device of digital human |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T05%3A05%3A01IST&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=LU%20ZENG&rft.date=2022-11-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115331265A%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 |