WEKO3
アイテム
{"_buckets": {"deposit": "a4d5a81d-33b8-45b9-bfbe-ef212a7ec92d"}, "_deposit": {"created_by": 14, "id": "4942", "owners": [14], "pid": {"revision_id": 0, "type": "depid", "value": "4942"}, "status": "published"}, "_oai": {"id": "oai:kyutech.repo.nii.ac.jp:00004942", "sets": ["24"]}, "author_link": ["19864", "399", "402", "1615", "404"], "control_number": "4942", "item_1689815586683": {"attribute_name": "CRID", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "https://cir.nii.ac.jp/crid/1390282679451771008", "subitem_relation_type_select": "URI"}}]}, "item_21_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2014-04-25", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "1", "bibliographicPageEnd": "74", "bibliographicPageStart": "67", "bibliographicVolumeNumber": "16", "bibliographic_titles": [{"bibliographic_title": "バイオメディカル・ファジィ・システム学会誌", "bibliographic_titleLang": "ja"}, {"bibliographic_title": "Journal of Biomedical Fuzzy Systems Association", "bibliographic_titleLang": "en"}]}]}, "item_21_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "近年注目されている技術分野としてITS(Intelligent Transport System)がある.特に画像から自動で人物や人を検出する技術は多くの研究者によって研究,開発されている.Dalalらによって提案されたHOG特徴量は多くの研究者が改良手法を提案しており,人検出手法において注目されている特徴量である.しかし,いずれの提案法も検出率と処理速度は十分とはいえない.本論文では,人(直立,歩行,走行中の人物)を対象に,HOG特徴量におけるビン数を領域ごとに可変にした,M-HOG(Multiple-HOG)特徴量と,色相の特徴を共起情報として用いる,RealAdaBoostアルゴリズムに基づく人検出法を提案し,高い検出率を保ったまま処理速度の高速化を実現する.また,共起情報を表現するために,2次元確率密度関数を導入する.提案法を従来法と比較する実験を行って処理性能の向上を確認した.", "subitem_description_language": "ja", "subitem_description_type": "Abstract"}, {"subitem_description": "Recently, car vision technologies have been paid much attention in the field of ITS(Intelligent Transport System). In particular, techniques for automatic detection of humans (or pedestrians) from images have been studied enthusiastically. The HOG feature proposed by Dalal and Triggs is a well known feature for representing and recognizing a human image. This is the reason why the feature is improved by many researchers. However, none of the previous improved techniques are satisfactory in the detection rate and the processing time. In this paper, we propose a method of detecting a human based on the M-HOG (Multiple-HOG) feature and RealAdaBoost using 2D probability density function. The proposed method can optimize the number of histogram\u0027s bin and express feature co-occurrence. We also propose a method using Hue (HSV Transform) and M-HOG feature. Experimental results show effectiveness of the proposed method compared to previous ones.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_21_link_62": {"attribute_name": "研究者情報", "attribute_value_mlt": [{"subitem_link_text": "https://hyokadb02.jimu.kyutech.ac.jp/html/35_ja.html", "subitem_link_url": "https://hyokadb02.jimu.kyutech.ac.jp/html/35_ja.html"}]}, "item_21_publisher_7": {"attribute_name": "出版社", "attribute_value_mlt": [{"subitem_publisher": "バイオメディカル・ファジィ・システム学会", "subitem_publisher_language": "ja"}]}, "item_21_relation_12": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "https://doi.org/10.24466/jbfsa.16.1_67", "subitem_relation_type_select": "DOI"}}]}, "item_21_rights_13": {"attribute_name": "著作権関連情報", "attribute_value_mlt": [{"subitem_rights": "Copyright (c) 2014 Biomedical Fuzzy Systems Association. 本文データは学協会の許諾に基づきCiNiiから複製したものである"}]}, "item_21_select_59": {"attribute_name": "査読の有無", "attribute_value_mlt": [{"subitem_select_item": "yes"}]}, "item_21_source_id_10": {"attribute_name": "NCID", "attribute_value_mlt": [{"subitem_source_identifier": "AA1145146X", "subitem_source_identifier_type": "NCID"}]}, "item_21_source_id_8": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "2424-2578", "subitem_source_identifier_type": "EISSN"}, {"subitem_source_identifier": "1345-1537", "subitem_source_identifier_type": "PISSN"}]}, "item_21_text_28": {"attribute_name": "論文ID(連携)", "attribute_value_mlt": [{"subitem_text_value": "10259448"}]}, "item_21_text_63": {"attribute_name": "連携ID", "attribute_value_mlt": [{"subitem_text_value": "5839"}]}, "item_21_version_type_58": {"attribute_name": "出版タイプ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "中島, 佑樹", "creatorNameLang": "ja"}, {"creatorName": "Nakashima, Yuuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "19864", "nameIdentifierScheme": "WEKO"}]}, {"creatorAffiliations": [{"affiliationNames": [{"affiliationNameLang": "ja"}]}], "creatorAlternatives": [{"creatorAlternative": "丹上, 結乃純", "creatorAlternativeLang": "ja"}, {"creatorAlternative": "Tanjo, Yui", "creatorAlternativeLang": "en"}, {"creatorAlternative": "タンジョウ, ユウイ", "creatorAlternativeLang": "ja-Kana"}], "creatorNames": [{"creatorName": "Tan, Joo kooi", "creatorNameLang": "en"}, {"creatorName": "タン, ジュークイ", "creatorNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "399", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "40363395", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000040363395"}, {"nameIdentifier": "7402302537", "nameIdentifierScheme": "Scopus著者ID", "nameIdentifierURI": "https://www.scopus.com/authid/detail.uri?authorId=7402302537"}, {"nameIdentifier": "35", "nameIdentifierScheme": "九工大研究者情報", "nameIdentifierURI": "https://hyokadb02.jimu.kyutech.ac.jp/html/35_ja.html"}]}, {"creatorAffiliations": [{"affiliationNames": [{"affiliationNameLang": "ja"}]}], "creatorAlternatives": [{"creatorAlternative": "Kamiya, Tohru", "creatorAlternativeLang": "en"}, {"creatorAlternative": "神谷, 亨", "creatorAlternativeLang": "ja"}, {"creatorAlternative": "カミヤ, トオル", "creatorAlternativeLang": "ja-Kana"}], "creatorNames": [{"creatorName": "Kim, Hyungseop", "creatorNameLang": "en"}, {"creatorName": "金, 亨燮", "creatorNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "402", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "80295005", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000080295005"}, {"nameIdentifier": "55739611300", "nameIdentifierScheme": "Scopus著者ID", "nameIdentifierURI": "https://www.scopus.com/authid/detail.uri?authorId=55739611300"}, {"nameIdentifier": "25", "nameIdentifierScheme": "九工大研究者情報", "nameIdentifierURI": "https://hyokadb02.jimu.kyutech.ac.jp/html/25_ja.html"}]}, {"creatorNames": [{"creatorName": "Morie, Takashi", "creatorNameLang": "en"}, {"creatorName": "森江, 隆", "creatorNameLang": "ja"}], "familyNames": [{"familyName": "Morie", "familyNameLang": "en"}, {"familyName": "森江", "familyNameLang": "ja"}], "givenNames": [{"givenName": "Takashi", "givenNameLang": "en"}, {"givenName": "隆", "givenNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "1615", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "20294530", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000020294530"}, {"nameIdentifier": "7005143434", "nameIdentifierScheme": "Scopus著者ID", "nameIdentifierURI": "https://www.scopus.com/authid/detail.uri?authorId=7005143434"}, {"nameIdentifier": "339", "nameIdentifierScheme": "九工大研究者情報", "nameIdentifierURI": "https://hyokadb02.jimu.kyutech.ac.jp/html/##_ja.html"}]}, {"creatorAffiliations": [{"affiliationNames": [{"affiliationNameLang": "ja"}]}], "creatorNames": [{"creatorName": "Ishikawa, Seiji", "creatorNameLang": "en"}, {"creatorName": "石川, 聖二", "creatorNameLang": "ja"}, {"creatorName": "イシカワ, セイジ", "creatorNameLang": "ja-Kana"}], "familyNames": [{"familyName": "Ishikawa", "familyNameLang": "en"}, {"familyName": "石川", "familyNameLang": "ja"}, {"familyName": "イシカワ", "familyNameLang": "ja-Kana"}], "givenNames": [{"givenName": "Seiji", "givenNameLang": "en"}, {"givenName": "聖二", "givenNameLang": "ja"}, {"givenName": "セイジ", "givenNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "404", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "90128116", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000090128116"}, {"nameIdentifier": "55539203500", "nameIdentifierScheme": "Scopus著者ID", "nameIdentifierURI": "https://www.scopus.com/authid/detail.uri?authorId=55539203500"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2017-04-20"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "110009818163.pdf", "filesize": [{"value": "7.6 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 7600000.0, "url": {"label": "110009818163.pdf", "url": "https://kyutech.repo.nii.ac.jp/record/4942/files/110009818163.pdf"}, "version_id": "b5af791d-9dd6-4a02-87f6-6ba775072a0a"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "人検出", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Multiple−HOG", "subitem_subject_scheme": "Other"}, {"subitem_subject": "共起", "subitem_subject_scheme": "Other"}, {"subitem_subject": "2次元確率密度関数", "subitem_subject_scheme": "Other"}, {"subitem_subject": "RealAdaBoost", "subitem_subject_scheme": "Other"}, {"subitem_subject": "コンピュータビジョン", "subitem_subject_scheme": "Other"}]}, "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": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "M-HOG特徴量と色相の共起情報を用いた人検出法", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "M-HOG特徴量と色相の共起情報を用いた人検出法", "subitem_title_language": "ja"}, {"subitem_title": "A Method of Human Detection Employing Co-occurrence Information on Multiple-HOG Feature and Color Feature", "subitem_title_language": "en"}]}, "item_type_id": "21", "owner": "14", "path": ["24"], "permalink_uri": "http://hdl.handle.net/10228/00006154", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2017-04-20"}, "publish_date": "2017-04-20", "publish_status": "0", "recid": "4942", "relation": {}, "relation_version_is_last": true, "title": ["M-HOG特徴量と色相の共起情報を用いた人検出法"], "weko_shared_id": -1}
M-HOG特徴量と色相の共起情報を用いた人検出法
http://hdl.handle.net/10228/00006154
http://hdl.handle.net/10228/0000615493b24ce4-94b3-4f0e-80e4-4c93651cd4e8
名前 / ファイル | ライセンス | アクション |
---|---|---|
110009818163.pdf (7.6 MB)
|
|
Item type | 学術雑誌論文 = Journal Article(1) | |||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
公開日 | 2017-04-20 | |||||||||||||||||
資源タイプ | ||||||||||||||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||||||
資源タイプ | journal article | |||||||||||||||||
タイトル | ||||||||||||||||||
言語 | ja | |||||||||||||||||
タイトル | M-HOG特徴量と色相の共起情報を用いた人検出法 | |||||||||||||||||
タイトル | ||||||||||||||||||
言語 | en | |||||||||||||||||
タイトル | A Method of Human Detection Employing Co-occurrence Information on Multiple-HOG Feature and Color Feature | |||||||||||||||||
言語 | ||||||||||||||||||
言語 | jpn | |||||||||||||||||
著者 |
中島, 佑樹
× 中島, 佑樹× タン, ジュークイ
WEKO
399
× 金, 亨燮
WEKO
402
× 森江, 隆× 石川, 聖二 |
|||||||||||||||||
抄録 | ||||||||||||||||||
内容記述タイプ | Abstract | |||||||||||||||||
内容記述 | 近年注目されている技術分野としてITS(Intelligent Transport System)がある.特に画像から自動で人物や人を検出する技術は多くの研究者によって研究,開発されている.Dalalらによって提案されたHOG特徴量は多くの研究者が改良手法を提案しており,人検出手法において注目されている特徴量である.しかし,いずれの提案法も検出率と処理速度は十分とはいえない.本論文では,人(直立,歩行,走行中の人物)を対象に,HOG特徴量におけるビン数を領域ごとに可変にした,M-HOG(Multiple-HOG)特徴量と,色相の特徴を共起情報として用いる,RealAdaBoostアルゴリズムに基づく人検出法を提案し,高い検出率を保ったまま処理速度の高速化を実現する.また,共起情報を表現するために,2次元確率密度関数を導入する.提案法を従来法と比較する実験を行って処理性能の向上を確認した. | |||||||||||||||||
言語 | ja | |||||||||||||||||
抄録 | ||||||||||||||||||
内容記述タイプ | Abstract | |||||||||||||||||
内容記述 | Recently, car vision technologies have been paid much attention in the field of ITS(Intelligent Transport System). In particular, techniques for automatic detection of humans (or pedestrians) from images have been studied enthusiastically. The HOG feature proposed by Dalal and Triggs is a well known feature for representing and recognizing a human image. This is the reason why the feature is improved by many researchers. However, none of the previous improved techniques are satisfactory in the detection rate and the processing time. In this paper, we propose a method of detecting a human based on the M-HOG (Multiple-HOG) feature and RealAdaBoost using 2D probability density function. The proposed method can optimize the number of histogram's bin and express feature co-occurrence. We also propose a method using Hue (HSV Transform) and M-HOG feature. Experimental results show effectiveness of the proposed method compared to previous ones. | |||||||||||||||||
言語 | en | |||||||||||||||||
書誌情報 |
ja : バイオメディカル・ファジィ・システム学会誌 en : Journal of Biomedical Fuzzy Systems Association 巻 16, 号 1, p. 67-74, 発行日 2014-04-25 |
|||||||||||||||||
出版社 | ||||||||||||||||||
言語 | ja | |||||||||||||||||
出版者 | バイオメディカル・ファジィ・システム学会 | |||||||||||||||||
DOI | ||||||||||||||||||
関連タイプ | isIdenticalTo | |||||||||||||||||
識別子タイプ | DOI | |||||||||||||||||
関連識別子 | https://doi.org/10.24466/jbfsa.16.1_67 | |||||||||||||||||
CRID | ||||||||||||||||||
関連タイプ | isIdenticalTo | |||||||||||||||||
識別子タイプ | URI | |||||||||||||||||
関連識別子 | https://cir.nii.ac.jp/crid/1390282679451771008 | |||||||||||||||||
NCID | ||||||||||||||||||
収録物識別子タイプ | NCID | |||||||||||||||||
収録物識別子 | AA1145146X | |||||||||||||||||
ISSN | ||||||||||||||||||
収録物識別子タイプ | EISSN | |||||||||||||||||
収録物識別子 | 2424-2578 | |||||||||||||||||
ISSN | ||||||||||||||||||
収録物識別子タイプ | PISSN | |||||||||||||||||
収録物識別子 | 1345-1537 | |||||||||||||||||
著作権関連情報 | ||||||||||||||||||
権利情報 | Copyright (c) 2014 Biomedical Fuzzy Systems Association. 本文データは学協会の許諾に基づきCiNiiから複製したものである | |||||||||||||||||
キーワード | ||||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | 人検出 | |||||||||||||||||
キーワード | ||||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | Multiple−HOG | |||||||||||||||||
キーワード | ||||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | 共起 | |||||||||||||||||
キーワード | ||||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | 2次元確率密度関数 | |||||||||||||||||
キーワード | ||||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | RealAdaBoost | |||||||||||||||||
キーワード | ||||||||||||||||||
主題Scheme | Other | |||||||||||||||||
主題 | コンピュータビジョン | |||||||||||||||||
出版タイプ | ||||||||||||||||||
出版タイプ | VoR | |||||||||||||||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||||||
査読の有無 | ||||||||||||||||||
値 | yes | |||||||||||||||||
研究者情報 | ||||||||||||||||||
https://hyokadb02.jimu.kyutech.ac.jp/html/35_ja.html | ||||||||||||||||||
論文ID(連携) | ||||||||||||||||||
10259448 | ||||||||||||||||||
連携ID | ||||||||||||||||||
5839 |