{"id":51925,"updated":"2025-01-22T06:59:38.027391+00:00","links":{},"created":"2025-01-18T23:16:21.802282+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00051925","sets":["1164:4619:4620:4625"]},"path":["4625"],"owner":"1","recid":"51925","title":["AAMの動的選択に基づく不特定人物の顔追跡"],"pubdate":{"attribute_name":"公開日","attribute_value":"2008-01-17"},"_buckets":{"deposit":"5e90b087-e9bb-4dd0-9293-f9f7b7a95112"},"_deposit":{"id":"51925","pid":{"type":"depid","value":"51925","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"AAMの動的選択に基づく不特定人物の顔追跡","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"AAMの動的選択に基づく不特定人物の顔追跡"},{"subitem_title":"Person-Independent Face Tracking Based on Dynamic AAM Selection","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2008-01-17","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"情報通信研究機構"},{"subitem_text_value":"情報通信研究機構"},{"subitem_text_value":"京都大学"},{"subitem_text_value":"京都大学"},{"subitem_text_value":"京都大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Information and Communication Technology","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Information and Communication Technology","subitem_text_language":"en"},{"subitem_text_value":"Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"Kyoto 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/51925/files/IPSJ-CVIM08161006.pdf"},"date":[{"dateType":"Available","dateValue":"2010-01-17"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM08161006.pdf","filesize":[{"value":"771.7 kB"}],"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":"d4028bb2-1af6-41a2-a60c-9c70f177717e","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":"小林, 亮博"},{"creatorName":"佐竹, 純二"},{"creatorName":"平山, 高嗣"},{"creatorName":"川嶋, 宏彰"},{"creatorName":"松山, 隆司"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Akihiro, KOBAYASHI","creatorNameLang":"en"},{"creatorName":"Junji, SATAKE","creatorNameLang":"en"},{"creatorName":"Takatsugu, HIRAYAMA","creatorNameLang":"en"},{"creatorName":"Hiroaki, KAWASHIMA","creatorNameLang":"en"},{"creatorName":"Takashi, MATSUYAMA","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":"本研究では，情報提示システムの前に訪れた不特定のユーザに対して最適なモデルを選択することで，カメラ画像からリアルタイムで高精度に顔を追跡する方法を提案する．Active Appearance Model (AAM) は形状変化と見えの変化の相関を学習する手法で，顔などの非剛体の追跡に適している．しかし不特定人物の顔を追跡する上で学習データを過剰に用いると，個人の特徴を表す軸が失われるだけでなく，多くの局所解が生まれるため追跡精度が低下する．そこで本研究では学習データを，類似した人物が併合されるようにクラスタリングを行い，未知のユーザに類似した顔のクラスタを選択することで追跡精度を向上させる．本稿では，相互部分空間法を用いてクラスタリングを行う手法を提案し，leave-one-out法で評価した結果について報告する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper proposes a real-time high-precision method to track an unknown face in front of an information system by selecting appropriate model to a video image. Active Appearance Model (AAM) can track a non-rigid object such as a face, because AAM learns the correlation between shape and texture. However, when AAM tracks an unknown face, excessive training data increases tracking errors because of truncating axes which shows characteristics of individuals and of additional local minima generated by the data. In order to increase accuracy of tracking unknown face, we build clusters from training data sets and select a model based on the cluster includes similar face with the unknown face. This paper shows a method of clustering and selecting the cluster based on Mutual Subspace Method, and the result of estimation by leave-one-out.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"40","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":"35","bibliographicIssueDates":{"bibliographicIssueDate":"2008-01-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3(2008-CVIM-161)","bibliographicVolumeNumber":"2008"}]},"relation_version_is_last":true,"weko_creator_id":"1"}}