{"updated":"2025-01-21T21:38:13.591030+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00074240","sets":["1164:4619:6274:6423"]},"path":["6423"],"owner":"10","recid":"74240","title":["剛体変換の整合性に基づく頑健な距離画像の位置合わせ"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-05-12"},"_buckets":{"deposit":"2bfc620e-6ecf-4688-91f7-0362f833af78"},"_deposit":{"id":"74240","pid":{"type":"depid","value":"74240","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"剛体変換の整合性に基づく頑健な距離画像の位置合わせ","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"剛体変換の整合性に基づく頑健な距離画像の位置合わせ"},{"subitem_title":"A Globally Convergence Algorithm for Range Image Registration Based on Consistency Evaluation of Rigid Transformation of Correspondences","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"卒論セッションダイジェスト2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2011-05-12","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京農工大学大学院"},{"subitem_text_value":"東京農工大学大学院"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School, Tokyo University of Agriculture and Technology","subitem_text_language":"en"},{"subitem_text_value":"Graduate School, Tokyo University of Agriculture and Technology","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/74240/files/IPSJ-CVIM11177024.pdf"},"date":[{"dateType":"Available","dateValue":"2013-05-12"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM11177024.pdf","filesize":[{"value":"2.1 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":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"3c579249-2f74-4514-bfbe-a715f182da3d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2011 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山田, 眞伍"},{"creatorName":"清水, 郁子"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shingo, Yamada","creatorNameLang":"en"},{"creatorName":"Ikuko, Shimizu","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，剛体変換の整合性を保証する 2 枚の距離画像の位置合わせ手法を提案する．本手法では，グラフカーネルアルゴリズムを用いることにより，特徴点の対応付けのあらゆる組合せの中で，対応点間を関係付ける剛体変換が整合している組合せを求め，剛体変換が整合する複数の対応点の組合せのなかで，最も類似度が優れている特徴点の対応付けの組合せを求める．本手法では，剛体変換の整合性を評価するために，3 組の特徴点からなる三角形の対応付けを用いる．このとき，すべての可能な三角形の対応は非常に膨大になるが，まず特徴点の全ての 1 対 1 対応のなかで対応の一意性の制約や距離の制約を満たす 1 対 1 対応の組合せを求め，整合する 1 対 1 対応の組合せの中からのみ 3 組を選択して三角形を生成することにより，候補を絞り込む．対応付けられた点の類似度の評価は SIFT を用いる．実験により，提案手法は様々モデルに対し適用可能であり，頑健であることを確認した．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this paper, a globally convergent algorithm for registration of two range images is proposed. Our method finds the consistent combinations of the corresponding feature point pairs with largest similarity by formulating as graph-based optimization problem. The consistency of rigid transformations is evaluated using triplets of feature point pairs. While the number of the all possible triplets of feature point pairs are very large, we reduce the candidates of the triplets based on the shape consistency, one-to-one correspondence assumption, and disntance consistency of all pairs of feature points. By introducing the graph kernel algorithm, the globally optimal combination of the triplets of feature point pairs is found by evaluating the similarity robustly using SIFT. Experimental results show that our algorithm is robust and available about valious models.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2011-05-12","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"24","bibliographicVolumeNumber":"2011-CVIM-177"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"created":"2025-01-18T23:31:53.100964+00:00","id":74240,"links":{}}