{"created":"2025-01-18T23:16:15.096316+00:00","updated":"2025-01-22T07:04:47.824145+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00051779","sets":["1164:4619:4620:4622"]},"path":["4622"],"owner":"1","recid":"51779","title":["Boostingを用いたボリュームデータからの人体姿勢推定"],"pubdate":{"attribute_name":"公開日","attribute_value":"2008-08-29"},"_buckets":{"deposit":"68f43b0b-704a-4e97-a1b2-3aebf6d3c222"},"_deposit":{"id":"51779","pid":{"type":"depid","value":"51779","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"Boostingを用いたボリュームデータからの人体姿勢推定","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Boostingを用いたボリュームデータからの人体姿勢推定"},{"subitem_title":"Human pose estimation using volumetric features and boosting approach","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2008-08-29","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"大阪大学大学院情報科学研究科／大阪大学サイバーメデイアセンター"},{"subitem_text_value":"大阪大学大学院情報科学研究科／大阪大学サイバーメデイアセンター"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Grauate School of Infomation Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Grauate School of Infomation Science and Technology, Osaka University / Cybermedia Center, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Grauate School of Infomation Science and Technology, Osaka University / Cybermedia Center, Osaka University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/51779/files/IPSJ-CVIM08164023.pdf"},"date":[{"dateType":"Available","dateValue":"2010-08-29"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM08164023.pdf","filesize":[{"value":"2.9 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"5880b7ff-4f32-4aa2-aecb-d186ab00231e","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2008 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"平, 亮介"},{"creatorName":"中澤, 篤志"},{"creatorName":"竹村, 治雄"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Ryosuke, Taira","creatorNameLang":"en"},{"creatorName":"Atsushi, Nakazawa","creatorNameLang":"en"},{"creatorName":"Haruo, Takemura","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"ボリュームデータから人体姿勢推定を行う事例ベースの手法を提案する．人体モデルを用いた人体姿勢推定において，関節角の初期パラメータをどう得るかは重要な問題である．その問題に対し，本手法では，モーションキャプチャデータから多量のサンプル（事例） を k-mean 法によりクラスタリングしておき，入力された被験者の姿勢に最も類似したクラスを選択することで解決する．クラス判別には，クラスタリングされたサンプルに対し AdaBoost アルゴリズムによる学習を行った， 2 値の識別器を用いる．特徴量には， 3 次元特徴である Volumetric Feature を多次元特徴ベクトルとして用いる．最終的に，識別器から得られたクラスの代表姿勢を収束法によるモデルフィッティングの初期姿勢として用いることで，安定かつ正確な姿勢推定を行うことができる．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Recently, considerable research has been conducted on markerless human-body motion capture using volume data. Most studies have used articulated body models that consist of primitives such as cylinders or ellipaoids. However, the methods that use such models require very good initial parameters. This paper proposes a method to find the human posture parameter from just a single frame without any knowledge of previous frames. We first prepare sample volume data which takes various poatures, and then cluster them according to the direction of body links. The volumetric feature vector ia acquired for each sample and they are learned via the AdaBoost algorithm. The resulting classifier is used for estimating input volume data, and the matched class can be used as an initial parameter for tracking based methods.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"148","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"143","bibliographicIssueDates":{"bibliographicIssueDate":"2008-08-29","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"82(2008-CVIM-164)","bibliographicVolumeNumber":"2008"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":51779,"links":{}}