WEKO3
AND
アイテム
{"_buckets": {"deposit": "f179a732-b1a4-44cc-ad34-f8d1e82f6c5a"}, "_deposit": {"id": "21706", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "21706"}, "status": "published"}, "_oai": {"id": "oai:nagoya.repo.nii.ac.jp:00021706"}, "item_10_alternative_title_19": {"attribute_name": "\u305d\u306e\u4ed6\u306e\u8a00\u8a9e\u306e\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_alternative_title": "A study on a method for stable pedestrian detection against pose changes with generative learning"}]}, "item_10_biblio_info_6": {"attribute_name": "\u66f8\u8a8c\u60c5\u5831", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2011-05-12", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "49", "bibliographicPageEnd": "132", "bibliographicPageStart": "127", "bibliographicVolumeNumber": "111", "bibliographic_titles": [{"bibliographic_title": "\u96fb\u5b50\u60c5\u5831\u901a\u4fe1\u5b66\u4f1a\u6280\u8853\u7814\u7a76\u5831\u544a. MI, \u533b\u7528\u753b\u50cf"}]}]}, "item_10_description_4": {"attribute_name": "\u6284\u9332", "attribute_value_mlt": [{"subitem_description": "\u8fd1\u5e74,\u8eca\u8f09\u30ab\u30e1\u30e9\u3067\u64ae\u5f71\u3055\u308c\u305f\u753b\u50cf\u304b\u3089\u6b69\u884c\u8005\u3092\u691c\u51fa\u3059\u308b\u7814\u7a76\u304c\u6ce8\u76ee\u3055\u308c\u3066\u3044\u308b.\u3057\u304b\u3057,\u59ff\u52e2\u5909\u5316\u304c\u5927\u304d\u304f,\u304b\u3064\u69d8\u3005\u306a\u80cc\u666f\u306b\u5b58\u5728\u3059\u308b\u6b69\u884c\u8005\u3092\u691c\u51fa\u3059\u308b\u3053\u3068\u306f\u5bb9\u6613\u3067\u306f\u306a\u3044.\u672c\u7814\u7a76\u3067\u306f,\u8eca\u8f09\u30ab\u30e1\u30e9\u753b\u50cf\u304b\u3089\u306e\u6b69\u884c\u8005\u691c\u51fa\u306b\u304a\u3044\u3066,\u591a\u69d8\u306a\u59ff\u52e2\u5909\u5316\u306b\u5bfe\u5fdc\u3059\u308b\u305f\u3081\u306e\u624b\u6cd5\u3092\u63d0\u6848\u3059\u308b.\u753b\u50cf\u4e2d\u306e\u6b69\u884c\u8005\u306e\u898b\u3048\u3092\u7279\u5fb4\u3068\u3057\u305f\u5f93\u6765\u306e\u6b69\u884c\u8005\u691c\u51fa\u624b\u6cd5\u3067\u306f,\u6b69\u884c\u8005\u306e\u59ff\u52e2\u5909\u5316\u3084\u6b69\u884c\u8005\u3092\u53d6\u308a\u5dfb\u304f\u74b0\u5883\u306e\u5909\u5316\u306b\u5bfe\u5fdc\u3059\u308b\u305f\u3081\u306b,\u5b66\u7fd2\u7528\u306b\u4e8b\u524d\u306b\u5927\u91cf\u306e\u6b69\u884c\u8005\u753b\u50cf\u3092\u4eba\u624b\u3067\u53ce\u96c6\u3059\u308b\u5fc5\u8981\u304c\u3042\u3063\u305f.\u63d0\u6848\u624b\u6cd5\u3067\u306f\u3053\u306e\u554f\u984c\u306b\u5bfe\u3057\u3066,\u5c11\u6570\u306e\u6b69\u884c\u8005\u753b\u50cf\u3092\u3044\u304f\u3064\u304b\u306e\u59ff\u52e2\u30af\u30e9\u30b9\u306b\u5206\u985e\u3057\u305f\u5f8c\u306b,\u59ff\u52e2\u30af\u30e9\u30b9\u3054\u3068\u306b\u591a\u69d8\u306a\u6b69\u884c\u8005\u753b\u50cf\u3092\u751f\u6210\u3057,\u3055\u3089\u306b\u3053\u306e\u59ff\u52e2\u30af\u30e9\u30b9\u3092\u30c6\u30f3\u30d7\u30ec\u30fc\u30c8\u3068\u3057\u305f\u30de\u30eb\u30c1\u30c6\u30f3\u30d7\u30ec\u30fc\u30c8\u578b\u306e\u8b58\u5225\u5668\u3092\u69cb\u7bc9\u3059\u308b\u3053\u3068\u3067\u89e3\u6c7a\u3092\u56f3\u308b.\u5b9f\u9a13\u306e\u7d50\u679c,\u5f93\u6765\u624b\u6cd5\u306b\u6bd4\u3079\u3066\u63d0\u6848\u624b\u6cd5\u306e\u691c\u51fa\u7cbe\u5ea6\u306f\u5927\u304d\u304f\u5411\u4e0a\u3057,\u305d\u306e\u6709\u52b9\u6027\u3092\u78ba\u8a8d\u3057\u305f.Recently, pedestrian detection from in-vehicle camera images is being focused. However, it is difficult to detect pedestrians due to the variety of their poses and backgrounds. To tackle this problem, we propose a method to detect various pedestrians from in-vehicle camera images. To deal with changes of pedestrians\u0027 pose and environment, most existing methods making use of their appearance require to prepare a lot of pedestrian images manually. The proposed method classifies a small number of pedestrian images into several pose classes and then generates various pedestrian images from each pose class. Finally, the proposed method constructs a classifier based on multiple templates from each pedestrian pose. Experimental results showed that the detection accuracy of the method outperformed existing methods, and we confirmed its effectiveness. [Note]This document is an informal handout distributed at an IEICE TC-PRMU workshop.", "subitem_description_type": "Abstract"}]}, "item_10_identifier_60": {"attribute_name": "URI", "attribute_value_mlt": [{"subitem_identifier_type": "URI", "subitem_identifier_uri": "http://ci.nii.ac.jp/naid/110008725866/"}, {"subitem_identifier_type": "HDL", "subitem_identifier_uri": "http://hdl.handle.net/2237/23855"}]}, "item_10_publisher_32": {"attribute_name": "\u51fa\u7248\u8005", "attribute_value_mlt": [{"subitem_publisher": "\u4e00\u822c\u793e\u56e3\u6cd5\u4eba\u96fb\u5b50\u60c5\u5831\u901a\u4fe1\u5b66\u4f1a"}]}, "item_10_relation_40": {"attribute_name": "\u30b7\u30ea\u30fc\u30ba", "attribute_value_mlt": [{"subitem_relation_name": [{"subitem_relation_name_text": "IEICE Technical Report;IE2011-31, PRMU2011-23, MI2011-23"}]}]}, "item_10_rights_12": {"attribute_name": "\u6a29\u5229", "attribute_value_mlt": [{"subitem_rights": "(c)\u4e00\u822c\u793e\u56e3\u6cd5\u4eba\u96fb\u5b50\u60c5\u5831\u901a\u4fe1\u5b66\u4f1a \u672c\u6587\u30c7\u30fc\u30bf\u306f\u5b66\u5354\u4f1a\u306e\u8a31\u8afe\u306b\u57fa\u3065\u304dCiNii\u304b\u3089\u8907\u88fd\u3057\u305f\u3082\u306e\u3067\u3042\u308b"}]}, "item_10_select_15": {"attribute_name": "\u8457\u8005\u7248\u30d5\u30e9\u30b0", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_10_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "0913-5685", "subitem_source_identifier_type": "ISSN"}]}, "item_creator": {"attribute_name": "\u8457\u8005", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "\u5409\u7530, \u82f1\u53f2"}], "nameIdentifiers": [{"nameIdentifier": "64371", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u51fa\u53e3, \u5927\u8f14"}], "nameIdentifiers": [{"nameIdentifier": "64372", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u4e95\u624b, \u4e00\u90ce"}], "nameIdentifiers": [{"nameIdentifier": "64373", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u6751\u702c, \u6d0b"}], "nameIdentifiers": [{"nameIdentifier": "64374", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u5f8c\u85e4, \u90a6\u535a"}], "nameIdentifiers": [{"nameIdentifier": "64375", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u6728\u6751, \u597d\u514b"}], "nameIdentifiers": [{"nameIdentifier": "64376", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u5185\u85e4, \u8cb4\u5fd7"}], "nameIdentifiers": [{"nameIdentifier": "64377", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "YOSHIDA, Hidefumi"}], "nameIdentifiers": [{"nameIdentifier": "64378", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "DEGUCHI, Daisuke"}], "nameIdentifiers": [{"nameIdentifier": "64379", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "IDE, Ichiro"}], "nameIdentifiers": [{"nameIdentifier": "64380", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "MURASE, Hiroshi"}], "nameIdentifiers": [{"nameIdentifier": "64381", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "GOTO, Kunihiro"}], "nameIdentifiers": [{"nameIdentifier": "64382", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "KIMURA, Yoshikatsu"}], "nameIdentifiers": [{"nameIdentifier": "64383", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "NAITO, Takashi"}], "nameIdentifiers": [{"nameIdentifier": "64384", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "\u30d5\u30a1\u30a4\u30eb\u60c5\u5831", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2018-02-21"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "110008725866.pdf", "filesize": [{"value": "1.5 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1500000.0, "url": {"label": "110008725866.pdf", "url": "https://nagoya.repo.nii.ac.jp/record/21706/files/110008725866.pdf"}, "version_id": "412d7bed-dbee-476f-8a93-dd98507c5833"}]}, "item_keyword": {"attribute_name": "\u30ad\u30fc\u30ef\u30fc\u30c9", "attribute_value_mlt": [{"subitem_subject": "\u6b69\u884c\u8005\u691c\u51fa", "subitem_subject_scheme": "Other"}, {"subitem_subject": "\u751f\u6210\u578b\u5b66\u7fd2\u6cd5", "subitem_subject_scheme": "Other"}, {"subitem_subject": "HOG", "subitem_subject_scheme": "Other"}, {"subitem_subject": "SVM", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Pedestrian detection", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Generative learning", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "\u8a00\u8a9e", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "\u8cc7\u6e90\u30bf\u30a4\u30d7", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "\u751f\u6210\u578b\u5b66\u7fd2\u6cd5\u3092\u7528\u3044\u305f\u59ff\u52e2\u5909\u5316\u306b\u9811\u5065\u306a\u6b69\u884c\u8005\u691c\u51fa\u306e\u691c\u8a0e(\u4e00\u822c\u30bb\u30c3\u30b7\u30e7\u30f3,\u533b\u7528\u753b\u50cf\u51e6\u7406\u5206\u91ce\u306b\u304a\u3051\u308b\u8a08\u6e2c\u30fb\u8a8d\u8b58\u30fb\u7406\u89e3)", "item_titles": {"attribute_name": "\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_title": "\u751f\u6210\u578b\u5b66\u7fd2\u6cd5\u3092\u7528\u3044\u305f\u59ff\u52e2\u5909\u5316\u306b\u9811\u5065\u306a\u6b69\u884c\u8005\u691c\u51fa\u306e\u691c\u8a0e(\u4e00\u822c\u30bb\u30c3\u30b7\u30e7\u30f3,\u533b\u7528\u753b\u50cf\u51e6\u7406\u5206\u91ce\u306b\u304a\u3051\u308b\u8a08\u6e2c\u30fb\u8a8d\u8b58\u30fb\u7406\u89e3)"}]}, "item_type_id": "10", "owner": "1", "path": ["312/313/314"], "permalink_uri": "http://hdl.handle.net/2237/23855", "pubdate": {"attribute_name": "\u516c\u958b\u65e5", "attribute_value": "2016-03-16"}, "publish_date": "2016-03-16", "publish_status": "0", "recid": "21706", "relation": {}, "relation_version_is_last": true, "title": ["\u751f\u6210\u578b\u5b66\u7fd2\u6cd5\u3092\u7528\u3044\u305f\u59ff\u52e2\u5909\u5316\u306b\u9811\u5065\u306a\u6b69\u884c\u8005\u691c\u51fa\u306e\u691c\u8a0e(\u4e00\u822c\u30bb\u30c3\u30b7\u30e7\u30f3,\u533b\u7528\u753b\u50cf\u51e6\u7406\u5206\u91ce\u306b\u304a\u3051\u308b\u8a08\u6e2c\u30fb\u8a8d\u8b58\u30fb\u7406\u89e3)"], "weko_shared_id": null}
生成型学習法を用いた姿勢変化に頑健な歩行者検出の検討(一般セッション,医用画像処理分野における計測・認識・理解)
http://hdl.handle.net/2237/23855
dd034bb6-61d7-4f0b-81de-4ae5689e7375
名前 / ファイル | ライセンス | アクション | |
---|---|---|---|
![]() |
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2016-03-16 | |||||
タイトル | ||||||
タイトル | 生成型学習法を用いた姿勢変化に頑健な歩行者検出の検討(一般セッション,医用画像処理分野における計測・認識・理解) | |||||
その他のタイトル | ||||||
その他のタイトル | A study on a method for stable pedestrian detection against pose changes with generative learning | |||||
著者 |
吉田, 英史
× 吉田, 英史× 出口, 大輔× 井手, 一郎× 村瀬, 洋× 後藤, 邦博× 木村, 好克× 内藤, 貴志× YOSHIDA, Hidefumi× DEGUCHI, Daisuke× IDE, Ichiro× MURASE, Hiroshi× GOTO, Kunihiro× KIMURA, Yoshikatsu× NAITO, Takashi |
|||||
権利 | ||||||
権利情報 | (c)一般社団法人電子情報通信学会 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 | 歩行者検出 | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | 生成型学習法 | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | HOG | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | SVM | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Pedestrian detection | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Generative learning | |||||
抄録 | ||||||
内容記述 | 近年,車載カメラで撮影された画像から歩行者を検出する研究が注目されている.しかし,姿勢変化が大きく,かつ様々な背景に存在する歩行者を検出することは容易ではない.本研究では,車載カメラ画像からの歩行者検出において,多様な姿勢変化に対応するための手法を提案する.画像中の歩行者の見えを特徴とした従来の歩行者検出手法では,歩行者の姿勢変化や歩行者を取り巻く環境の変化に対応するために,学習用に事前に大量の歩行者画像を人手で収集する必要があった.提案手法ではこの問題に対して,少数の歩行者画像をいくつかの姿勢クラスに分類した後に,姿勢クラスごとに多様な歩行者画像を生成し,さらにこの姿勢クラスをテンプレートとしたマルチテンプレート型の識別器を構築することで解決を図る.実験の結果,従来手法に比べて提案手法の検出精度は大きく向上し,その有効性を確認した.Recently, pedestrian detection from in-vehicle camera images is being focused. However, it is difficult to detect pedestrians due to the variety of their poses and backgrounds. To tackle this problem, we propose a method to detect various pedestrians from in-vehicle camera images. To deal with changes of pedestrians' pose and environment, most existing methods making use of their appearance require to prepare a lot of pedestrian images manually. The proposed method classifies a small number of pedestrian images into several pose classes and then generates various pedestrian images from each pose class. Finally, the proposed method constructs a classifier based on multiple templates from each pedestrian pose. Experimental results showed that the detection accuracy of the method outperformed existing methods, and we confirmed its effectiveness. [Note]This document is an informal handout distributed at an IEICE TC-PRMU workshop. | |||||
内容記述タイプ | Abstract | |||||
出版者 | ||||||
出版者 | 一般社団法人電子情報通信学会 | |||||
言語 | ||||||
言語 | jpn | |||||
資源タイプ | ||||||
資源タイプresource | http://purl.org/coar/resource_type/c_6501 | |||||
タイプ | journal article | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 0913-5685 | |||||
書誌情報 |
電子情報通信学会技術研究報告. MI, 医用画像 巻 111, 号 49, p. 127-132, 発行日 2011-05-12 |
|||||
著者版フラグ | ||||||
値 | publisher | |||||
シリーズ | ||||||
関連名称 | ||||||
関連名称 | IEICE Technical Report;IE2011-31, PRMU2011-23, MI2011-23 | |||||
URI | ||||||
識別子 | http://ci.nii.ac.jp/naid/110008725866/ | |||||
識別子タイプ | URI | |||||
URI | ||||||
識別子 | http://hdl.handle.net/2237/23855 | |||||
識別子タイプ | HDL |