{"updated":"2025-01-19T15:04:01.706445+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00208992","sets":["581:10433:10434"]},"path":["10434"],"owner":"44499","recid":"208992","title":["人検出タスクにおける単体LRF環境での深層学習モデルの提案とその評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-01-15"},"_buckets":{"deposit":"334e25eb-b716-408a-b541-43aada5e3d8f"},"_deposit":{"id":"208992","pid":{"type":"depid","value":"208992","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"人検出タスクにおける単体LRF環境での深層学習モデルの提案とその評価","author_link":["525727","525729","525730","525728"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"人検出タスクにおける単体LRF環境での深層学習モデルの提案とその評価"},{"subitem_title":"Proposal and its Evaluation of Deep Learning Model for Human Detection Task in a Single LRF Environment","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[特集：5G時代の社会を創るモバイル・高度交通システム] レーザレンジファインダ，深層学習，点群，1クラス分類","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2021-01-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"金沢工業大学"},{"subitem_text_value":"金沢工業大学"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Kanazawa Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Kanazawa Institute of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/208992/files/IPSJ-JNL6201029.pdf","label":"IPSJ-JNL6201029.pdf"},"date":[{"dateType":"Available","dateValue":"2023-01-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6201029.pdf","filesize":[{"value":"1.4 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"13382f32-3db9-4b22-b7ab-1408aecac804","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"小原, 裕輝"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中沢, 実"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuki, Kohara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Minoru, Nakazawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","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_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"単体のレーザレンジファインダ（LRF）を用いた人の検出手法は，貨物運搬ロボットなどに使われる．これらの検出では，入力が検出対象であるかどうかの判定に，hand-crafted特徴量と正であるか偽であるか分類する1クラス分類モデルを使用した手法が適用されている．本論文では，1クラス分類モデルへの入力をhand-crafted特徴量ではなく，深層学習モデルによって生成された特徴量に置き換えた手法を提案する．実験では，hand-crafted特徴を使用した手法との検出率の比較を行い，パフォーマンスが一部向上したことを示す．また，ロボットの利用など実応用のために，Jetson Nanoを使用して提案手法の処理速度の評価を行い実用可能性を評価した．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Human detection using a single laser range finder (LRF) has been used for autonomous vehicles such as cargo carrying robots. In these detections, a method using hand-crafted feature values and a one-class classification model is applied to determine whether an object is a detection object or not. In this paper, we propose a method in which the input to a one-class classification model is replaced by features generated by a deep learning model instead of hand-crafted features. In the experiment, the detection rate was compared with the method using the hand-crafted feature. Furthermore, the processing speed was measured using the Jetson Nano to verify its practical applicability.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"253","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"246","bibliographicIssueDates":{"bibliographicIssueDate":"2021-01-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"62"}]},"relation_version_is_last":true,"item_2_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.20729/00208890","subitem_identifier_reg_type":"JaLC"}]},"weko_creator_id":"44499"},"created":"2025-01-19T01:10:20.066683+00:00","id":208992,"links":{}}