{"updated":"2025-01-19T15:13:37.737587+00:00","links":{},"created":"2025-01-19T01:18:37.985677+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00218222","sets":["1164:3616:10863:10936"]},"path":["10936"],"owner":"44499","recid":"218222","title":["［チュートリアル講演］高精度・高効率なロボットビジョンの構築法：深層学習用データセット生成法とハードウェア実装の両面より"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-06-02"},"_buckets":{"deposit":"d5958de8-f9fe-448e-911d-9b4dec48a509"},"_deposit":{"id":"218222","pid":{"type":"depid","value":"218222","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"［チュートリアル講演］高精度・高効率なロボットビジョンの構築法：深層学習用データセット生成法とハードウェア実装の両面より","author_link":["567001","567000"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"［チュートリアル講演］高精度・高効率なロボットビジョンの構築法：深層学習用データセット生成法とハードウェア実装の両面より"},{"subitem_title":"How to build a High-Precision and Efficient Robot Vision: Dataset Generation and Hardware Implementation for Deep Learning","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"チュートリアル講演","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-06-02","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"九州工業大学大学院生命体工学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate Schoolo of Life Science and Systems Engineering, Kyushu Institute of 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/218222/files/IPSJ-AVM22117012.pdf","label":"IPSJ-AVM22117012.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-AVM22117012.pdf","filesize":[{"value":"1.5 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"27"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"4027a90b-dd76-4aaf-adbb-7e8cb6f743ed","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"田向, 権"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hakaru, Tamukoh","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10438399","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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8582","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本チュートリアル講演では，高精度かつ高効率なロボットビジョンの構築法として，独自データセットの半自動生成法と，深層ニューラルネットワーク（DNN: Deep Neural Network）の Field Programmable Gate Array（FPGA）の簡便な実装例を示す．独自データセットの半自動生成法においては，人手では膨大な時間がかかるアノテーション作業を完全に削減することで，約 2 時間程度で実用に耐えうる深層学習用のデータセットが生成できることを示す． RoboCup や World Robot Summit といった競技会を通した実環境下での評価結果を示す．また，DNN の FPGA 実装においては，YOLO v3 tiny を題材にその実例を示す．本講演を通し，人工知能のエッジ応用において大きな障壁となる，データセット作成と電力問題に関して解決策の一例を示す．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This tutorial lecture explains a construction method for high-precision and efficient robot vision that includes a semi-automatic dataset generation method and an implementation method of deep neural networks (DNNs) on field-programmable gate arrays (FPGAs). The proposed dataset generation method ultimately reduces the time-consuming manual annotation process, and a generated dataset for DNNs can be prepared in about two hours. I show the evaluation results for a DNN trained by the generated dataset under real-world conditions through robot competitions such as RoboCup and World Robot Summit. We also show an example of FPGA implementation of YOLO v3 tiny. Through this presentation, I show examples of solutions for dataset preparation and power-consumption issues, which are significant barriers to edge applications of artificial intelligence.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"4","bibliographic_titles":[{"bibliographic_title":"研究報告オーディオビジュアル複合情報処理（AVM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-06-02","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"12","bibliographicVolumeNumber":"2022-AVM-117"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":218222}