ログイン
言語:

WEKO3

  • トップ
  • コミュニティ
  • ランキング
AND
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

{"_buckets": {"deposit": "1f281045-6909-4df1-a3e5-d754e29a567c"}, "_deposit": {"id": "13065", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "13065"}, "status": "published"}, "_oai": {"id": "oai:nagoya.repo.nii.ac.jp:00013065"}, "item_10_biblio_info_6": {"attribute_name": "\u66f8\u8a8c\u60c5\u5831", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2008-04-01", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "4", "bibliographicPageEnd": "1100", "bibliographicPageStart": "1091", "bibliographicVolumeNumber": "E91-D", "bibliographic_titles": [{"bibliographic_title": "IEICE transactions on information and systems"}]}]}, "item_10_description_4": {"attribute_name": "\u6284\u9332", "attribute_value_mlt": [{"subitem_description": "We propose the construction of an appearance manifold with embedded view-dependent covariance matrix to recognize 3D objects which are influenced by geometric distortions and quality degradation effects. The appearance manifold is used to capture the pose variability, while the covariance matrix is used to learn the distribution of samples for gaining noise-invariance. However, since the appearance of an object in the captured image is different for every different pose, the covariance matrix value is also different for every pose position. Therefore, it is important to embed view-dependent covariance matrices in the manifold of an object. We propose two models of constructing an appearance manifold with view-dependent covariance matrix, called the View-dependent Covariance matrix by training-Point Interpolation (VCPI) and View-dependent Covariance matrix by Eigenvector Interpolation (VCEI) methods. Here, the embedded view-dependent covariance matrix of the VCPI method is obtained by interpolating every training-points from one pose to other training-points in a consecutive pose. Meanwhile, in the VCEI method, the embedded view-dependent covariance matrix is obtained by interpolating only the eigenvectors and eigenvalues without considering the correspondences of each training image. As it embeds the covariance matrix in manifold, our view-dependent covariance matrix methods are robust to any pose changes and are also noise invariant. Our main goal is to construct a robust and efficient manifold with embedded view-dependent covariance matrix for recognizing objects from images which are influenced with various degradation effects.", "subitem_description_type": "Abstract"}]}, "item_10_identifier_60": {"attribute_name": "URI", "attribute_value_mlt": [{"subitem_identifier_type": "URI", "subitem_identifier_uri": "http://www.ieice.org/jpn/trans_online/index.html"}, {"subitem_identifier_type": "HDL", "subitem_identifier_uri": "http://hdl.handle.net/2237/14959"}]}, "item_10_publisher_32": {"attribute_name": "\u51fa\u7248\u8005", "attribute_value_mlt": [{"subitem_publisher": "Institute of Electronics, Information and Communication Engineers"}]}, "item_10_rights_12": {"attribute_name": "\u6a29\u5229", "attribute_value_mlt": [{"subitem_rights": "Copyright (C) 2008 IEICE"}]}, "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": "0916-8532", "subitem_source_identifier_type": "ISSN"}]}, "item_creator": {"attribute_name": "\u8457\u8005", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Lina"}], "nameIdentifiers": [{"nameIdentifier": "41098", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "TAKAHASHI, Tomokazu"}], "nameIdentifiers": [{"nameIdentifier": "41099", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "IDE, Ichiro"}], "nameIdentifiers": [{"nameIdentifier": "41100", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "MURASE, Hiroshi"}], "nameIdentifiers": [{"nameIdentifier": "41101", "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": "2018-02-20"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "355.pdf", "filesize": [{"value": "1.1 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1100000.0, "url": {"label": "355.pdf", "url": "https://nagoya.repo.nii.ac.jp/record/13065/files/355.pdf"}, "version_id": "e681c8a4-eca9-4467-8830-278a1ec9cbf4"}]}, "item_keyword": {"attribute_name": "\u30ad\u30fc\u30ef\u30fc\u30c9", "attribute_value_mlt": [{"subitem_subject": "3D object recognition", "subitem_subject_scheme": "Other"}, {"subitem_subject": "appearance manifold", "subitem_subject_scheme": "Other"}, {"subitem_subject": "view-dependent covariance matrix", "subitem_subject_scheme": "Other"}, {"subitem_subject": "eigenvector interpolation", "subitem_subject_scheme": "Other"}, {"subitem_subject": "eigenvalue interpolation", "subitem_subject_scheme": "Other"}, {"subitem_subject": "eigenspace", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "\u8a00\u8a9e", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "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": "Construction of Appearance Manifold with Embedded View-Dependent Covariance Matrix for 3D Object Recognition", "item_titles": {"attribute_name": "\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_title": "Construction of Appearance Manifold with Embedded View-Dependent Covariance Matrix for 3D Object Recognition"}]}, "item_type_id": "10", "owner": "1", "path": ["312/313/314"], "permalink_uri": "http://hdl.handle.net/2237/14959", "pubdate": {"attribute_name": "\u516c\u958b\u65e5", "attribute_value": "2011-06-28"}, "publish_date": "2011-06-28", "publish_status": "0", "recid": "13065", "relation": {}, "relation_version_is_last": true, "title": ["Construction of Appearance Manifold with Embedded View-Dependent Covariance Matrix for 3D Object Recognition"], "weko_shared_id": 3}
  1. A500 情報学部/情報学研究科・情報文化学部・情報科学研究科
  2. A500a 雑誌掲載論文
  3. 学術雑誌

Construction of Appearance Manifold with Embedded View-Dependent Covariance Matrix for 3D Object Recognition

http://hdl.handle.net/2237/14959
f38687aa-2fbf-42e9-800d-5d6b995b663b
名前 / ファイル ライセンス アクション
355.pdf 355.pdf (1.1 MB)
Item type 学術雑誌論文 / Journal Article(1)
公開日 2011-06-28
タイトル
タイトル Construction of Appearance Manifold with Embedded View-Dependent Covariance Matrix for 3D Object Recognition
著者 Lina

× Lina

WEKO 41098

Lina

Search repository
TAKAHASHI, Tomokazu

× TAKAHASHI, Tomokazu

WEKO 41099

TAKAHASHI, Tomokazu

Search repository
IDE, Ichiro

× IDE, Ichiro

WEKO 41100

IDE, Ichiro

Search repository
MURASE, Hiroshi

× MURASE, Hiroshi

WEKO 41101

MURASE, Hiroshi

Search repository
権利
権利情報 Copyright (C) 2008 IEICE
キーワード
主題Scheme Other
主題 3D object recognition
キーワード
主題Scheme Other
主題 appearance manifold
キーワード
主題Scheme Other
主題 view-dependent covariance matrix
キーワード
主題Scheme Other
主題 eigenvector interpolation
キーワード
主題Scheme Other
主題 eigenvalue interpolation
キーワード
主題Scheme Other
主題 eigenspace
抄録
内容記述 We propose the construction of an appearance manifold with embedded view-dependent covariance matrix to recognize 3D objects which are influenced by geometric distortions and quality degradation effects. The appearance manifold is used to capture the pose variability, while the covariance matrix is used to learn the distribution of samples for gaining noise-invariance. However, since the appearance of an object in the captured image is different for every different pose, the covariance matrix value is also different for every pose position. Therefore, it is important to embed view-dependent covariance matrices in the manifold of an object. We propose two models of constructing an appearance manifold with view-dependent covariance matrix, called the View-dependent Covariance matrix by training-Point Interpolation (VCPI) and View-dependent Covariance matrix by Eigenvector Interpolation (VCEI) methods. Here, the embedded view-dependent covariance matrix of the VCPI method is obtained by interpolating every training-points from one pose to other training-points in a consecutive pose. Meanwhile, in the VCEI method, the embedded view-dependent covariance matrix is obtained by interpolating only the eigenvectors and eigenvalues without considering the correspondences of each training image. As it embeds the covariance matrix in manifold, our view-dependent covariance matrix methods are robust to any pose changes and are also noise invariant. Our main goal is to construct a robust and efficient manifold with embedded view-dependent covariance matrix for recognizing objects from images which are influenced with various degradation effects.
内容記述タイプ Abstract
出版者
出版者 Institute of Electronics, Information and Communication Engineers
言語
言語 eng
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 0916-8532
書誌情報 IEICE transactions on information and systems

巻 E91-D, 号 4, p. 1091-1100, 発行日 2008-04-01
著者版フラグ
値 publisher
URI
識別子 http://www.ieice.org/jpn/trans_online/index.html
識別子タイプ URI
URI
識別子 http://hdl.handle.net/2237/14959
識別子タイプ HDL
戻る
0
views
See details
Views

Versions

Ver.1 2021-03-01 13:35:44.142256
Show All versions

Share

Mendeley CiteULike Twitter Facebook Print Addthis

Cite as

Export

OAI-PMH
  • OAI-PMH JPCOAR
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by CERN Data Centre & Invenio


Powered by CERN Data Centre & Invenio