{"updated":"2025-01-21T06:58:56.296972+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00112464","sets":["1164:3027:7765:7837"]},"path":["7837"],"owner":"11","recid":"112464","title":["自撮り動画像の背景変動を利用した人物領域抽出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2015-01-07"},"_buckets":{"deposit":"67cd571d-dff9-4b9a-bf1c-c9ee8cbda015"},"_deposit":{"id":"112464","pid":{"type":"depid","value":"112464","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"自撮り動画像の背景変動を利用した人物領域抽出","author_link":["33314","33315"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"自撮り動画像の背景変動を利用した人物領域抽出"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"実世界UI","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2015-01-07","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"関西学院大学大学院理工学研究科人間システム工学専攻"},{"subitem_text_value":"関西学院大学大学院理工学研究科人間システム工学専攻"}]},"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/112464/files/IPSJ-HCI15161010.pdf"},"date":[{"dateType":"Available","dateValue":"2017-01-07"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HCI15161010.pdf","filesize":[{"value":"1.9 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":"33"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"d7e45b76-5712-4df4-9b28-186a9bbb32c2","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2015 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"中川, 裕太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"河野, 恭之"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA1221543X","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":"本研究は手持ちカメラを撮影者自身に向けて撮影した “自撮り” 動画像から人物領域を推定して抽出する手法を提案する.撮影者自身と背景を写せる自撮りは手軽に自身の体験や状況を他者と共有できる.しかし一般的な自撮りではレンズと撮影者の距離が腕の長さに制限されてしまうため,どれも背景が広く写らない自撮り特有の構図になってしまう.そこで本研究では自撮り動画像から人物領域だけを自動で抽出し,加工や修正,または合成用素材に利用しやすい状態にして編集することで自撮り特有の構図に縛られない自由な自撮り写真の作成に活用するための人物領域抽出手法を提案する.自撮り動画像はカメラを持った腕を前方に伸ばして撮影者自身が写り込むようにし,カメラは撮影者自身に向けたまま身体が中心軸になるように体を回転させて撮影する.撮影者自身はフレームのほぼ中央に写り込み続けてあまり時間軸に対して変動しない人物領域となるが,その周囲の背景領域ではフレーム内に写り込む背景が時間軸に対して大きく変動する.また撮影者の背面に隠れて写り込まなかった背景空間がカメラの回転移動により背景領域に写り込むため,前景である人物領域とその背面に隠れていた背景の差分を検出できる.これら背景領域と人物領域の特徴に着目して各領域を推定し,推定結果を基に GrabCut アルゴリズムを利用して人物領域を抽出する.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告ヒューマンコンピュータインタラクション(HCI)"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2015-01-07","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"10","bibliographicVolumeNumber":"2015-HCI-161"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:54:14.944388+00:00","id":112464,"links":{}}