{"created":"2023-07-27T06:52:28.961744+00:00","id":46430,"links":{},"metadata":{"_buckets":{"deposit":"88f57431-c78e-4bb4-a619-15fc4e08b637"},"_deposit":{"created_by":18,"id":"46430","owners":[18],"pid":{"revision_id":0,"type":"depid","value":"46430"},"status":"published"},"_oai":{"id":"oai:kanazawa-u.repo.nii.ac.jp:00046430","sets":["2812:2813:2821"]},"author_link":["2278","80437"],"item_9_biblio_info_8":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2014-06-14","bibliographicIssueDateType":"Issued"},"bibliographicPageStart":"5p.","bibliographicVolumeNumber":"2010-04-01 - 2013-03-31","bibliographic_titles":[{"bibliographic_title":"平成24(2012)年度 科学研究費補助金 基盤研究(C) 研究成果報告書"},{"bibliographic_title":"2013 Fiscal Year Final Research Report","bibliographic_titleLang":"en"}]}]},"item_9_creator_33":{"attribute_name":"著者別表示","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{}],"nameIdentifiers":[{},{}]}]},"item_9_description_21":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"本研究の目的は汎用で高精度な画像認識アルゴリズムを考案し、これに基づく実時間SOCプロセッサを開発し、性能を実証することである。このSOCは汎用CPUとアフィン動き分割回路から構成される。左右一組のステレオ画像を入力すると動き分割回路が物体に対応する領域を抽出する。CPUは分割で得た勾配画像モーメントを特徴量としてSVMによるクラス分類を行う。そして次の時間の画像を入力し、動き分割回路がアフィン動きモデル推定により物体を追跡する。本SOCによる画像認識は車両検出・追跡を初め、幅広く応用できる。試作したSOCの面積は4.1mm角、最大周波数は94MHz、スループットはVGA91fpsであった。","subitem_description_type":"Abstract"},{"subitem_description":"This study proposes a novel image recognition algorithm for general purpose with high accuracy. We also develop an SOC based on this algorithm with real-time performance. The SOC consists of a general purpose CPU and a processor dedicated to affine motion segmentation. The processor divides an image into regions corresponding to objects captured in stereo images. The processor calculates gradient image moment to estimate a parallax between regions of an identical object in the left and right images. The CPU classifies objects with SVM (Support Vector Machine). The SVM uses the image gradient moment again as an image feature for recognition. Then the motion segmentation processor tracks objects with affine motion model estimation using an image of the next time. Image recogniton by the SOC is applicable to many applications such as vehicle detection and tracking. The chip area of the SOC is 4.1 mm square. The operating frequency is 94 MHz. The processing throughput is VGA 91 fps.","subitem_description_type":"Abstract"}]},"item_9_description_22":{"attribute_name":"内容記述","attribute_value_mlt":[{"subitem_description":"研究課題/領域番号:22560325, 研究期間(年度):2010-04-01 - 2013-03-31","subitem_description_type":"Other"},{"subitem_description":"出典：研究課題「確率的領域分割と超平面クラス分類による高精度・汎用・実時間画像認識SOCの研究」課題番号22560325\n（KAKEN：科学研究費助成事業データベース（国立情報学研究所）） \n（https://kaken.nii.ac.jp/report/KAKENHI-PROJECT-22560325/22560325seika/）を加工して作成","subitem_description_type":"Other"}]},"item_9_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.24517/00052762","subitem_identifier_reg_type":"JaLC"}]},"item_9_publisher_17":{"attribute_name":"公開者","attribute_value_mlt":[{"subitem_publisher":"金沢大学理工研究域電子情報通信学系"}]},"item_9_relation_28":{"attribute_name":"関連URI","attribute_value_mlt":[{"subitem_relation_name":[{"subitem_relation_name_text":"https://kaken.nii.ac.jp/search/?qm=30324106"}],"subitem_relation_type_id":{"subitem_relation_type_id_text":"https://kaken.nii.ac.jp/search/?qm=30324106","subitem_relation_type_select":"URI"}},{"subitem_relation_name":[{"subitem_relation_name_text":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-22560325/"}],"subitem_relation_type_id":{"subitem_relation_type_id_text":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-22560325/","subitem_relation_type_select":"URI"}},{"subitem_relation_name":[{"subitem_relation_name_text":"https://kaken.nii.ac.jp/report/KAKENHI-PROJECT-22560325/22560325seika/"}],"subitem_relation_type_id":{"subitem_relation_type_id_text":"https://kaken.nii.ac.jp/report/KAKENHI-PROJECT-22560325/22560325seika/","subitem_relation_type_select":"URI"}}]},"item_9_version_type_25":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_ab4af688f83e57aa","subitem_version_type":"AM"}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2018-11-15"}],"displaytype":"detail","filename":"TE-PR-MIYAMA-M-kaken 2014-5p.pdf","filesize":[{"value":"655.1 kB"}],"format":"application/pdf","licensetype":"license_11","mimetype":"application/pdf","url":{"label":"TE-PR-MIYAMA-M-kaken 2014-5p.pdf","url":"https://kanazawa-u.repo.nii.ac.jp/record/46430/files/TE-PR-MIYAMA-M-kaken 2014-5p.pdf"},"version_id":"0255bc32-ce4d-4f2b-9aec-de40c707ee54"}]},"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":"research report","resourceuri":"http://purl.org/coar/resource_type/c_18ws"}]},"item_title":"確率的領域分割と超平面クラス分類による高精度・汎用・実時間画像認識SOCの研究","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"確率的領域分割と超平面クラス分類による高精度・汎用・実時間画像認識SOCの研究"},{"subitem_title":"A study on real-time image recognition SOC with affine motion segmentation","subitem_title_language":"en"}]},"item_type_id":"9","owner":"18","path":["2821"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-11-15"},"publish_date":"2018-11-15","publish_status":"0","recid":"46430","relation_version_is_last":true,"title":["確率的領域分割と超平面クラス分類による高精度・汎用・実時間画像認識SOCの研究"],"weko_creator_id":"18","weko_shared_id":-1},"updated":"2023-07-27T12:31:13.963547+00:00"}