{"updated":"2025-01-21T11:31:19.290501+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00100902","sets":["934:6391:7564:7565"]},"path":["7565"],"owner":"11","recid":"100902","title":["距離画像による空間情報マッチングに基づくマーカレスARシステムの設計と実装"],"pubdate":{"attribute_name":"公開日","attribute_value":"2014-04-23"},"_buckets":{"deposit":"ff422c21-4f4f-4453-9ce3-03f28333bf46"},"_deposit":{"id":"100902","pid":{"type":"depid","value":"100902","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"距離画像による空間情報マッチングに基づくマーカレスARシステムの設計と実装","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"距離画像による空間情報マッチングに基づくマーカレスARシステムの設計と実装"},{"subitem_title":"Markerless AR System Based on Spatial Information Matching Using Depth Image","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[コンシューマ・システム論文] ポイントクラウド，平面オブジェクト，PCA，RANSAC法","subitem_subject_scheme":"Other"}]},"item_type_id":"3","publish_date":"2014-04-23","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋大学大学院工学研究科"},{"subitem_text_value":"名古屋大学大学院工学研究科"},{"subitem_text_value":"名古屋大学大学院工学研究科"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, 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/100902/files/IPSJ-TCDS0401003.pdf"},"date":[{"dateType":"Available","dateValue":"2016-04-23"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TCDS0401003.pdf","filesize":[{"value":"6.2 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":"47"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"1a8e575c-a6e3-4371-a117-cbb52855e8dc","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2014 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山川, 健司"},{"creatorName":"梶, 克彦"},{"creatorName":"河口, 信夫"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kenji, Yamakawa","creatorNameLang":"en"},{"creatorName":"Katsuhiko, Kaji","creatorNameLang":"en"},{"creatorName":"Nobuo, Kawaguchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_3_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12628043","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_3_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2186-5728","subitem_source_identifier_type":"ISSN"}]},"item_3_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"実世界の映像にデジタル情報を重畳表示するAR（拡張現実感）には，姿勢追従や位置推定が必要となる．ARの実現手法にはいくつか種類があるが，本研究では室内におけるマーカレスARを対象としたロバストな位置推定を最終目標とする．本稿では，環境光の影響を低減させるために距離画像センサを用い，距離画像やポイントクラウドの処理に基づいて空間情報のマッチングを行う手法を提案する．本研究では，天井，壁，机等の室内の平面オブジェクトの多さに注目する．ARの対象とその周囲の空間情報（以下，シーン）を平面の組合せのパターンで表現し，観測可能な平面の数，平面間の角度，平行な平面間の距離をシーンの特徴量として算出する．本稿では，距離画像やポイントクラウドの処理によって，撮影したシーンから平面を抽出する手法について説明する．その後，シーンの特徴量を用いた平面オブジェクト同定およびシーン同定手法を提案する．評価実験では，実際の室内環境を用いてマッチングを行った．その結果，すべての学習済み環境が正しく同定でき，未学習の環境は該当なしの結果を得た．","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Augmented Reality (AR) is a technology to overlay some information at a related position in camera images. Hence, an estimation of position and direction of camera is necessary to achieve AR. Though there are several methods, our goal is to develop a robust estimation method for indoor Markerless AR. Particularly, we use a depth image sensor to avoid the influence of environmental lights, and we propose a method to match the spatial information by processing depth images and point clouds. In indoor environments, there are many planar objects, for example ceilings, walls, tables and so on. Therefore, we extract three features from the combinations of such planar objects to describe a scene (spatial information around a target of AR). The features are as follows: the number of observed planes, the angles between planes and the distances between parallel planes. In this paper, we introduce how to extract planes at first. Then, we propose how to identify planar objects and scenes by using such features. Experiments were made to show effectiveness of the method in a real indoor environment. As a result, all of the learned scenes were recognized properly and a non-learned scene was rejected.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"21","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌コンシューマ・デバイス＆システム（CDS）"}],"bibliographicPageStart":"12","bibliographicIssueDates":{"bibliographicIssueDate":"2014-04-23","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"4"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:46:35.785398+00:00","id":100902,"links":{}}