{"links":{},"id":2001847,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02001847","sets":["1164:4619:11919:1744767391283"]},"path":["1744767391283"],"owner":"80578","recid":"2001847","title":["手関節位置の三次元時系列情報による動作認識"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2025-05-08"},"_buckets":{"deposit":"f3442660-9e7f-4360-81c5-331667ebc09a"},"_deposit":{"id":"2001847","pid":{"type":"depid","value":"2001847","revision_id":0},"owners":[80578],"status":"published","created_by":80578},"item_title":"手関節位置の三次元時系列情報による動作認識","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"手関節位置の三次元時系列情報による動作認識","subitem_title_language":"ja"},{"subitem_title":"Motion recognition by three-dimensional time series information of hand joint positions","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"CVIM","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2025-05-08","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"岡山大学大学院ヘルスシステム統合科学研究科"},{"subitem_text_value":"岡山大学大学院ヘルスシステム統合科学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Interdisciplinary Science and Engineering in Health System OKAYAMA UNIVERSITY","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Interdisciplinary Science and Engineering in Health System OKAYAMA 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/2001847/files/IPSJ-CVIM25242016.pdf","label":"IPSJ-CVIM25242016.pdf"},"date":[{"dateType":"Available","dateValue":"2027-05-08"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM25242016.pdf","filesize":[{"value":"1.6 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"af302c5b-abf6-4719-a756-796ed961774f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2025 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"笠松,一聖"}]},{"creatorNames":[{"creatorName":"中澤,篤志"}]}]},"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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"手の動作認識は，医療や福祉，スポーツなど幅広い分野で重要であるが，多様で複雑な動作の分類や，非接触で簡便に計測する手法が乏しいという課題があった．一方近年，2次元・3次元のイメージセンサが容易に入手可能となり，1台の装置を用いて3次元の手関節位置を推定できる技術が進展し，実利用面で新たな可能性が生まれている．本研究では，この非接触で3次元の手形状が計測できる技術を活用することで，様々な手の動作データを収集し，sktimeライブラリが提供する複数のアルゴリズムを用いて分類する手法を開発・検証した．10種類の動作を対象に，4人の被験者から動作ごとに収集したデータを学習・テストに用いた場合，正答率は最も良いもので98.56%となった．次に動作ごとのデータを学習に使用し，10種類の動作を連続して行った連続動作データをテストに使用した．入力データとして手の関節位置をそのまま使用する絶対座標，手首からの相対座標，指の関節角度，の3種類のデータを用いて比較した結果，絶対座標データの正答率は25.98%，相対座標データは52.86%，関節角度データは53.66%となり，関節角度を用いた分類の精度が最も高いことが示された．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2025-05-08","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"16","bibliographicVolumeNumber":"2025-CVIM-242"}]},"relation_version_is_last":true,"weko_creator_id":"80578"},"created":"2025-04-28T02:29:48.601246+00:00","updated":"2025-04-28T02:29:52.655997+00:00"}