{"created":"2025-01-19T01:12:36.665188+00:00","updated":"2025-01-19T17:47:42.238093+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00211451","sets":["1164:4061:10490:10587"]},"path":["10587"],"owner":"44499","recid":"211451","title":["寝姿体圧画像からの3次元関節位置推定の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-05-27"},"_buckets":{"deposit":"6085d1e4-ef48-4027-8740-c3b6c6a5381a"},"_deposit":{"id":"211451","pid":{"type":"depid","value":"211451","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"寝姿体圧画像からの3次元関節位置推定の検討","author_link":["537274","537275","537273","537272"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"寝姿体圧画像からの3次元関節位置推定の検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人間状態推定・理解","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-05-27","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋大学情報学研究科"},{"subitem_text_value":"名古屋大学情報学研究科"},{"subitem_text_value":"名古屋大学未来社会創造機構"},{"subitem_text_value":"名古屋大学情報学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Informatics, Nagoya university","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Nagoya university","subitem_text_language":"en"},{"subitem_text_value":"Institute of Innovation for Future Society, Nagoya university","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Nagoya 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/211451/files/IPSJ-UBI21070005.pdf","label":"IPSJ-UBI21070005.pdf"},"date":[{"dateType":"Available","dateValue":"2023-05-27"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-UBI21070005.pdf","filesize":[{"value":"1.7 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":"36"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"1fe3c4d6-7749-46d3-89e4-2c86fde37564","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"加藤, 寛貴"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"榎堀, 優"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"吉田, 直人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"間瀬, 健二"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11838947","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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8698","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"寝姿勢時における褥瘡発生危険部位の特定には，関節位置まで含めた姿勢推定が重要である．カメラ画像を用いて推定する手法には，布団によるオクルージョン問題・プライバシー問題が存在するため，我々は寝姿勢時のベッド面にかかる体圧画像（以降，寝姿体圧画像）からの関節位置推定を研究している．既存研究では，寝姿体圧画像からの 2 次元関節位置推定に注力してきた．しかし，2 次元関節位置では手足の交差状況などが不明であり，自重による過剰圧迫の評価や浮いている関節点の対応不要箇所などの抽出が行えない．そこで本稿では，推定された 2 次元関節位置から 3 次元関節位置を推定する手法を検討する．本稿では GAN を用いて 2 次元関節位置から 3 次元関節位置を推定する手法に，寝姿勢種別を考慮するネットワーク構造の拡張と寝姿勢らしい推定を行うための 2 種類の損失を組み合わせることで推定精度の向上を試みた．SLP データセットで交差検証を行い，誤差を 17.091 から 9.825 へ約 42.5% の誤差低減を実現した．これは, 日本人の標準肩幅 42.696cm にスケーリングした場合に約 5.171cm の誤差改善に相当する．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告ユビキタスコンピューティングシステム（UBI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-05-27","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicVolumeNumber":"2021-UBI-70"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":211451,"links":{}}