{"created":"2023-06-19T10:30:07.505709+00:00","id":10302,"links":{},"metadata":{"_buckets":{"deposit":"fa66d7d7-130b-4b4f-928e-0081509676ce"},"_deposit":{"created_by":18,"id":"10302","owners":[18],"pid":{"revision_id":0,"type":"depid","value":"10302"},"status":"published"},"_oai":{"id":"oai:muroran-it.repo.nii.ac.jp:00010302","sets":["216:442","46"]},"author_link":["57928","57927","54336","57926"],"item_79_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2018","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicPageEnd":"I_139","bibliographicPageStart":"I_131","bibliographicVolumeNumber":"74","bibliographic_titles":[{"bibliographic_title":"土木学会論文集Ｅ１（舗装工学）","bibliographic_titleLang":"ja"}]}]},"item_79_description_23":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_79_description_7":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"本研究では，路面性状測定車による高速道路の路面画像にConvolutional Neural Network（CNN）を適用し，ひび割れとパッチングを高精度で検出し，ひび割れ率を自動算出する手法を開発した．まず，目視スケッチ画像を基にひび割れ部等の小片領域を抽出し，CNNモデルの学習用データセットを自動生成した．小片領域サイズを複数設定し，モデルの精度比較を行ったところ，サイズ150以上では過学習となる可能性があり，90～120などの中間サイズではひび割れやパッチングの見逃し，誤検知が比較的少なくなることが分かった．モデルを路面画像に適用してひび割れ率を算出し，従来のスケッチ法と比較した．その結果，サイズ90（実寸3cm×3cm）で最も精度が良く，ひび割れ形状を細かく可視化できることを示した．","subitem_description_language":"ja","subitem_description_type":"Abstract"}]},"item_79_link_17":{"attribute_name":"出版者版へのリンク","attribute_value_mlt":[{"subitem_link_text":"10.2208/jscejpe.74.I_131","subitem_link_url":"https://doi.org/10.2208/jscejpe.74.I_131"}]},"item_79_link_5":{"attribute_name":"室蘭工業大学研究者データベースへのリンク","attribute_value_mlt":[{"subitem_link_text":"浅田 拓海（ASADA Takumi）","subitem_link_url":"http://rdsoran.muroran-it.ac.jp/html/100000065_ja.html"}]},"item_79_publisher_11":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"土木学会","subitem_publisher_language":"ja"}]},"item_79_relation_18":{"attribute_name":"DOI","attribute_value_mlt":[{"subitem_relation_type":"isIdenticalTo","subitem_relation_type_id":{"subitem_relation_type_id_text":"10.2208/jscejpe.74.I_131","subitem_relation_type_select":"DOI"}}]},"item_79_rights_19":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"© 2018 土木学会","subitem_rights_language":"ja"}]},"item_79_source_id_12":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2185-6559","subitem_source_identifier_type":"EISSN"}]},"item_79_subject_9":{"attribute_name":"日本十進分類法","attribute_value_mlt":[{"subitem_subject":"007","subitem_subject_scheme":"NDC"}]},"item_79_version_type_21":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_970fb48d4fbd8a85","subitem_version_type":"VoR"}]},"item_access_right":{"attribute_name":"アクセス権","attribute_value_mlt":[{"subitem_access_right":"open access","subitem_access_right_uri":"http://purl.org/coar/access_right/c_abf2"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorAffiliations":[{"affiliationNameIdentifiers":[{}],"affiliationNames":[{},{}]}],"creatorNames":[{"creatorName":"ASADA, Takumi","creatorNameLang":"en"},{"creatorName":"浅田, 拓海","creatorNameLang":"ja"},{"creatorName":"アサダ, タクミ","creatorNameLang":"ja-Kana"}],"familyNames":[{},{},{}],"givenNames":[{},{},{}],"nameIdentifiers":[{},{}]},{"creatorNames":[{"creatorName":"川村, 和将","creatorNameLang":"ja"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"石田, 篤徳","creatorNameLang":"ja"}],"nameIdentifiers":[{}]},{"creatorAffiliations":[{"affiliationNameIdentifiers":[],"affiliationNames":[{"affiliationName":""}]}],"creatorNames":[{"creatorName":"亀山, 修一","creatorNameLang":"ja"},{"creatorName":"KAMEYAMA, Shuichi","creatorNameLang":"en"},{"creatorName":"カメヤマ, シュウイチ","creatorNameLang":"ja-Kana"}],"familyNames":[{},{},{}],"givenNames":[{},{},{}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2020-07-20"}],"displaytype":"detail","filename":"JSCE_74_3_I131_139.pdf","filesize":[{"value":"2.1 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"JSCE_74_3_I131_139","objectType":"fulltext","url":"https://muroran-it.repo.nii.ac.jp/record/10302/files/JSCE_74_3_I131_139.pdf"},"version_id":"e44b7fd0-dcf7-43c2-bfd7-a6cb594b1c1f"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"pavement","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"crack","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"tracing","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"convolutional neural network","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"high resolution","subitem_subject_language":"en","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"Convolutional Neural Networkを用いたひび割れ・パッチングの高精度検出手法の開発","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Convolutional Neural Networkを用いたひび割れ・パッチングの高精度検出手法の開発","subitem_title_language":"ja"}]},"item_type_id":"79","owner":"18","path":["46","442"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2020-07-20"},"publish_date":"2020-07-20","publish_status":"0","recid":"10302","relation_version_is_last":true,"title":["Convolutional Neural Networkを用いたひび割れ・パッチングの高精度検出手法の開発"],"weko_creator_id":"18","weko_shared_id":-1},"updated":"2024-02-16T05:00:08.576330+00:00"}