{"created":"2025-01-19T01:44:19.123387+00:00","updated":"2025-01-19T08:02:26.096166+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00240237","sets":["6164:6165:6640:11802"]},"path":["11802"],"owner":"44499","recid":"240237","title":["Trackletによる物体アソシエーションの精度向上手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-19"},"_buckets":{"deposit":"f7482688-79ba-446b-9adb-4a74aafac7f0"},"_deposit":{"id":"240237","pid":{"type":"depid","value":"240237","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Trackletによる物体アソシエーションの精度向上手法","author_link":["658778","658777","658779","658780"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Trackletによる物体アソシエーションの精度向上手法"},{"subitem_title":"Approach for Improving Object Association Accuracy Using Tracklet","subitem_title_language":"en"}]},"item_type_id":"18","publish_date":"2024-06-19","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"立命館大学情報理工学部環境情報研究室"},{"subitem_text_value":"立命館大学情報理工学部環境情報研究室"},{"subitem_text_value":"株式会社ティアフォー"},{"subitem_text_value":"立命館大学情報理工学部環境情報研究室"}]},"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/240237/files/IPSJ-DICOMO2024121.pdf","label":"IPSJ-DICOMO2024121.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-19"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2024121.pdf","filesize":[{"value":"30.1 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":"44"}],"accessrole":"open_date","version_id":"699bb48a-bfc1-4455-a16d-96e60d9b5224","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"上田, 陽平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Zuofan, Fang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"斉藤, 之寛"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"西尾, 信彦"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"公道での自動運転では，事前想定していない未知物体の出現やセンサノイズの発生が多く存在し，物体検出のロバスト性向上が不可欠である．そこで複数のセンサを用いたマルチモーダルでの対応が注目されており，カメラと LiDAR がよく用いられる．しかし，カメラと LiDARの異なる出力特性のセンサをフュージョンする必要がある．マルチモーダルセンサーフュージョンではearly fusionやlate fusionといったものがあるが，late fusionにおいてそれぞれセンサー特性のアソシエーションに失敗すると実際は未知な物体に対し，既知物体のラベルを付与してしまう誤検出などが起こる原因となる．その結果，実際とは異なる位置に物体がいると判断し，自車両が緊急停止するような問題に発展する．そこで，本研究は物体検出を目的とし，カメラとLiDARによるLate Fusionにおいてtrackletを導入することで時系列の安定化を行う．評価の結果，既存技術と比較しアソシエーション精度が 7.5 向上した．アソシエーション精度の向上により，公道での自動運転下での物体検出のロバスト性向上への有用性を示した．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"890","bibliographic_titles":[{"bibliographic_title":"マルチメディア，分散，協調とモバイルシンポジウム2024論文集"}],"bibliographicPageStart":"883","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-19","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":240237,"links":{}}