MODEL GENERATION METHOD, MODEL GENERATION DEVICE, NON-TRANSITORY STORAGE MEDIUM, MOVING BODY POSITION

The invention provides a model generation method, a model generation device, a non-transitory storage medium, a moving body posture estimation method, and a moving body posture estimation device. A model generation method includes: indicating image coordinates in a two-dimensional image in which at...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HAMAJIMA AYA, NAKANISHI KATSUNORI, YAMAGUCHI YOHEI, NAKANO YUSUKE
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 HAMAJIMA AYA
NAKANISHI KATSUNORI
YAMAGUCHI YOHEI
NAKANO YUSUKE
description The invention provides a model generation method, a model generation device, a non-transitory storage medium, a moving body posture estimation method, and a moving body posture estimation device. A model generation method includes: indicating image coordinates in a two-dimensional image in which at least a moving body is captured as key points of the moving body, and creating training data from the two-dimensional image to which information relating to the key points is added; the image coordinates are image coordinates of at least one of vertexes of a rectangular shape formed by projecting an outer shape of the moving body on a path when the moving body is viewed from above; and performing machine learning using the training data, and generating a machine learning model for outputting the key points from a two-dimensional image in which at least a moving body is captured. 一种模型生成方法、模型生成装置、非瞬时性存储介质、移动体姿势推定方法以及移动体姿势推定装置。模型生成方法包括:将至少拍摄了移动体的2维图像中的图像坐标指示为所述移动体的关键点,将附加了与所述关键点相关的信息的所述2维图像制作为训练数据,所述图像坐标是从上部观察所述移动体时的所
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115700796A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115700796A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115700796A3</originalsourceid><addsrcrecordid>eNrjZEj19Xdx9VFwd_VzDXIM8fT3U_B1DfHwd9FRwJBwcQ3zdHbVUfDz99MNCXL0C_YM8Q-KVAgGko7urkB9Lp6hviB9YZ5-7gpO_i6RCgH-QEVAvTwMrGmJOcWpvFCam0HRzTXE2UM3tSA_PrW4IDE5NS-1JN7Zz9DQ1NzAwNzSzNGYGDUAgzQ04w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MODEL GENERATION METHOD, MODEL GENERATION DEVICE, NON-TRANSITORY STORAGE MEDIUM, MOVING BODY POSITION</title><source>esp@cenet</source><creator>HAMAJIMA AYA ; NAKANISHI KATSUNORI ; YAMAGUCHI YOHEI ; NAKANO YUSUKE</creator><creatorcontrib>HAMAJIMA AYA ; NAKANISHI KATSUNORI ; YAMAGUCHI YOHEI ; NAKANO YUSUKE</creatorcontrib><description>The invention provides a model generation method, a model generation device, a non-transitory storage medium, a moving body posture estimation method, and a moving body posture estimation device. A model generation method includes: indicating image coordinates in a two-dimensional image in which at least a moving body is captured as key points of the moving body, and creating training data from the two-dimensional image to which information relating to the key points is added; the image coordinates are image coordinates of at least one of vertexes of a rectangular shape formed by projecting an outer shape of the moving body on a path when the moving body is viewed from above; and performing machine learning using the training data, and generating a machine learning model for outputting the key points from a two-dimensional image in which at least a moving body is captured. 一种模型生成方法、模型生成装置、非瞬时性存储介质、移动体姿势推定方法以及移动体姿势推定装置。模型生成方法包括:将至少拍摄了移动体的2维图像中的图像坐标指示为所述移动体的关键点,将附加了与所述关键点相关的信息的所述2维图像制作为训练数据,所述图像坐标是从上部观察所述移动体时的所</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2023</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&amp;date=20230207&amp;DB=EPODOC&amp;CC=CN&amp;NR=115700796A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25562,76317</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230207&amp;DB=EPODOC&amp;CC=CN&amp;NR=115700796A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HAMAJIMA AYA</creatorcontrib><creatorcontrib>NAKANISHI KATSUNORI</creatorcontrib><creatorcontrib>YAMAGUCHI YOHEI</creatorcontrib><creatorcontrib>NAKANO YUSUKE</creatorcontrib><title>MODEL GENERATION METHOD, MODEL GENERATION DEVICE, NON-TRANSITORY STORAGE MEDIUM, MOVING BODY POSITION</title><description>The invention provides a model generation method, a model generation device, a non-transitory storage medium, a moving body posture estimation method, and a moving body posture estimation device. A model generation method includes: indicating image coordinates in a two-dimensional image in which at least a moving body is captured as key points of the moving body, and creating training data from the two-dimensional image to which information relating to the key points is added; the image coordinates are image coordinates of at least one of vertexes of a rectangular shape formed by projecting an outer shape of the moving body on a path when the moving body is viewed from above; and performing machine learning using the training data, and generating a machine learning model for outputting the key points from a two-dimensional image in which at least a moving body is captured. 一种模型生成方法、模型生成装置、非瞬时性存储介质、移动体姿势推定方法以及移动体姿势推定装置。模型生成方法包括:将至少拍摄了移动体的2维图像中的图像坐标指示为所述移动体的关键点,将附加了与所述关键点相关的信息的所述2维图像制作为训练数据,所述图像坐标是从上部观察所述移动体时的所</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZEj19Xdx9VFwd_VzDXIM8fT3U_B1DfHwd9FRwJBwcQ3zdHbVUfDz99MNCXL0C_YM8Q-KVAgGko7urkB9Lp6hviB9YZ5-7gpO_i6RCgH-QEVAvTwMrGmJOcWpvFCam0HRzTXE2UM3tSA_PrW4IDE5NS-1JN7Zz9DQ1NzAwNzSzNGYGDUAgzQ04w</recordid><startdate>20230207</startdate><enddate>20230207</enddate><creator>HAMAJIMA AYA</creator><creator>NAKANISHI KATSUNORI</creator><creator>YAMAGUCHI YOHEI</creator><creator>NAKANO YUSUKE</creator><scope>EVB</scope></search><sort><creationdate>20230207</creationdate><title>MODEL GENERATION METHOD, MODEL GENERATION DEVICE, NON-TRANSITORY STORAGE MEDIUM, MOVING BODY POSITION</title><author>HAMAJIMA AYA ; NAKANISHI KATSUNORI ; YAMAGUCHI YOHEI ; NAKANO YUSUKE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115700796A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>HAMAJIMA AYA</creatorcontrib><creatorcontrib>NAKANISHI KATSUNORI</creatorcontrib><creatorcontrib>YAMAGUCHI YOHEI</creatorcontrib><creatorcontrib>NAKANO YUSUKE</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HAMAJIMA AYA</au><au>NAKANISHI KATSUNORI</au><au>YAMAGUCHI YOHEI</au><au>NAKANO YUSUKE</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MODEL GENERATION METHOD, MODEL GENERATION DEVICE, NON-TRANSITORY STORAGE MEDIUM, MOVING BODY POSITION</title><date>2023-02-07</date><risdate>2023</risdate><abstract>The invention provides a model generation method, a model generation device, a non-transitory storage medium, a moving body posture estimation method, and a moving body posture estimation device. A model generation method includes: indicating image coordinates in a two-dimensional image in which at least a moving body is captured as key points of the moving body, and creating training data from the two-dimensional image to which information relating to the key points is added; the image coordinates are image coordinates of at least one of vertexes of a rectangular shape formed by projecting an outer shape of the moving body on a path when the moving body is viewed from above; and performing machine learning using the training data, and generating a machine learning model for outputting the key points from a two-dimensional image in which at least a moving body is captured. 一种模型生成方法、模型生成装置、非瞬时性存储介质、移动体姿势推定方法以及移动体姿势推定装置。模型生成方法包括:将至少拍摄了移动体的2维图像中的图像坐标指示为所述移动体的关键点,将附加了与所述关键点相关的信息的所述2维图像制作为训练数据,所述图像坐标是从上部观察所述移动体时的所</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN115700796A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title MODEL GENERATION METHOD, MODEL GENERATION DEVICE, NON-TRANSITORY STORAGE MEDIUM, MOVING BODY POSITION
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T18%3A22%3A09IST&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=HAMAJIMA%20AYA&rft.date=2023-02-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115700796A%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