{"updated":"2025-01-22T02:25:22.522220+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00062859","sets":["1164:4619:5663:5716"]},"path":["5716"],"owner":"10","recid":"62859","title":["人検出のための Real AdaBoost に基づく HOG 特徴量の効率的な削減法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-06-02"},"_buckets":{"deposit":"3be67480-e8a9-4bb8-8a2f-9b6f7f9af589"},"_deposit":{"id":"62859","pid":{"type":"depid","value":"62859","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"人検出のための Real AdaBoost に基づく HOG 特徴量の効率的な削減法","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"人検出のための Real AdaBoost に基づく HOG 特徴量の効率的な削減法"},{"subitem_title":"A Method for Reducing number of HOG Features based on Real AdaBoost","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"卒論セッション・概要発表2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2009-06-02","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"中部大学大学院工学研究科"},{"subitem_text_value":"中部大学大学院工学研究科"},{"subitem_text_value":"中部大学大学院工学研究科／オムロン株式会社"},{"subitem_text_value":"中部大学大学院工学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Chubu University","subitem_text_language":"en"},{"subitem_text_value":"Chubu University","subitem_text_language":"en"},{"subitem_text_value":"Chubu University / OMRON Corporation","subitem_text_language":"en"},{"subitem_text_value":"Chubu University","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/62859/files/IPSJ-CVIM09167032.pdf"},"date":[{"dateType":"Available","dateValue":"2011-06-02"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM09167032.pdf","filesize":[{"value":"1.1 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":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"d299fba9-e676-4631-854a-e94364adaf38","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2009 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"松島, 千佳"},{"creatorName":"山内, 悠嗣"},{"creatorName":"山下, 隆義"},{"creatorName":"藤吉, 弘亘"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Chika, Matsushima","creatorNameLang":"en"},{"creatorName":"Yuji, Yamauchi","creatorNameLang":"en"},{"creatorName":"Takayoshi, Yamashita","creatorNameLang":"en"},{"creatorName":"Hironobu, Fujiyoshi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本稿では，人検出のための Real AdaBoost に基づく HOG 特徴量の効率的な削減法を提案する．提案手法は，人検出において用いられる HOG 特徴量をバイナリパターン化することにより，特徴量数の削減を行い，必要なメモリ量を抑制することが可能となる．しかし，バイナリパターン化することにより，識別時に用いる確率密度分布が疎になる問題が発生する．そこで，学習時に Real AdaBoost を用いてバイナリパターンの統合を行い，密な確率密度分布を作成する．提案手法の有効性を確認するために，人の識別実験と処理に必要なメモリ量の比較を行う．その結果，HOG 特徴量と同程度の識別精度を維持し，処理に必要なメモリ量を削減することができた．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We propose an efficient method for reducing the number of HOG features based on Real AdaBoost. The proposed method can reduce the amount of memory required by converting the HOG features used in human detection to a binary pattern. Converting to a binary pattern, however, causes the problem of a sparse probability density distribution used in classification. Nevertheless, a dense probability density distribution can be achieved by using Real AdaBoost to integrate the binary pattern during training. To confirm the effectiveness of the proposed method, we conducted evaluation experiments and compared the amounts of memory required. The results show that the detection accuracy of the HOG features is retained, but less memory is required for the processing.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2009-06-02","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"32","bibliographicVolumeNumber":"2009-CVIM-167"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"created":"2025-01-18T23:24:43.946541+00:00","id":62859,"links":{}}