WEKO3
アイテム
{"_buckets": {"deposit": "9d8ab94c-4b75-4095-b6ca-1a9f89b95f1d"}, "_deposit": {"created_by": 21, "id": "3144", "owners": [21], "pid": {"revision_id": 0, "type": "depid", "value": "3144"}, "status": "published"}, "_oai": {"id": "oai:ir.soken.ac.jp:00003144", "sets": ["19"]}, "author_link": ["231", "230", "232"], "item_1_biblio_info_21": {"attribute_name": "書誌情報(ソート用)", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2012-03-23", "bibliographicIssueDateType": "Issued"}, "bibliographic_titles": [{}]}]}, "item_1_creator_2": {"attribute_name": "著者名", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "THOMAS, Diego"}], "nameIdentifiers": [{"nameIdentifier": "230", "nameIdentifierScheme": "WEKO"}]}]}, "item_1_creator_3": {"attribute_name": "フリガナ", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "トーマス, ディエゴ"}], "nameIdentifiers": [{"nameIdentifier": "231", "nameIdentifierScheme": "WEKO"}]}]}, "item_1_date_granted_11": {"attribute_name": "学位授与年月日", "attribute_value_mlt": [{"subitem_dategranted": "2012-03-23"}]}, "item_1_degree_grantor_5": {"attribute_name": "学位授与機関", "attribute_value_mlt": [{"subitem_degreegrantor": [{"subitem_degreegrantor_name": "総合研究大学院大学"}]}]}, "item_1_degree_name_6": {"attribute_name": "学位名", "attribute_value_mlt": [{"subitem_degreename": "博士(情報学)"}]}, "item_1_description_1": {"attribute_name": "ID", "attribute_value_mlt": [{"subitem_description": "2012052", "subitem_description_type": "Other"}]}, "item_1_description_12": {"attribute_name": "要旨", "attribute_value_mlt": [{"subitem_description": "3D modeling of a real scene stands for constructing a virtual representation\r\nof the scene, generally simplified that can be used or modified at\r\nour will. Constructing such a 3D model by hand is a laborious and time\r\nconsuming task, and automating the whole process has attracted growing interest\r\nin the computer vision field. In particular, the task of registering (i.e.\r\naligning) different parts of the scene (called range images) acquired from\r\ndifferent viewpoints is of crucial importance when constructing 3D models.\r\nDuring the last decades, researchers have concentrated their efforts on this\r\nproblem and proposed several methodologies to automatically register range\r\nimages. Thereby, key-point detectors and descriptors have been utilized to\r\nmatch points across different range images using geometric features or textural\r\nfeatures. Several similarity metrics have also been proposed to identify\r\nthe overlapping regions. In spite of the advantages of the current methods,\r\nseveral limitation cases have been reported. In particular, when the scene\r\nlacks in discriminative geometric features, the difficulty of accounting for\r\nthe changes in appearance of the scene observed in different poses, or from\r\ndifferent viewpoints, significantly degrades the performance of the current\r\nmethods. We address this issue by investigating the use of photometry (i.e.\r\nthe relationship between geometry, reflectance properties and illumination)\r\nfor range image registration. First, we propose a robust descriptor using\r\nalbedo that is permissive to errors in the illumination estimation. Second,\r\nwe propose an albedo extraction technique for specular surfaces that enlarges\r\nthe range of materials we can deal with. Third, we propose a photometric\r\nmetric under unknown lighting that allows registration of range images without\r\nany assumptions on the illumination. With these proposed methods, we\r\nsignificantly enlarge the practicability and range of applications of range\r\nimage registration.", "subitem_description_type": "Other"}]}, "item_1_description_7": {"attribute_name": "学位記番号", "attribute_value_mlt": [{"subitem_description": "総研大甲第1517号", "subitem_description_type": "Other"}]}, "item_1_select_14": {"attribute_name": "所蔵", "attribute_value_mlt": [{"subitem_select_item": "有"}]}, "item_1_select_16": {"attribute_name": "複写", "attribute_value_mlt": [{"subitem_select_item": "全文公開可"}]}, "item_1_select_17": {"attribute_name": "公開状況", "attribute_value_mlt": [{"subitem_select_item": "application/pdf"}]}, "item_1_select_8": {"attribute_name": "研究科", "attribute_value_mlt": [{"subitem_select_item": "複合科学研究科"}]}, "item_1_select_9": {"attribute_name": "専攻", "attribute_value_mlt": [{"subitem_select_item": "17 情報学専攻"}]}, "item_1_text_10": {"attribute_name": "学位授与年度", "attribute_value_mlt": [{"subitem_text_value": "2011"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "THOMAS, Diego", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "232", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2016-02-17"}], "displaytype": "simple", "download_preview_message": "", "file_order": 0, "filename": "甲1517_要旨.pdf", "filesize": [{"value": "329.4 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_11", "mimetype": "application/pdf", "size": 329400.0, "url": {"label": "要旨・審査要旨", "url": "https://ir.soken.ac.jp/record/3144/files/甲1517_要旨.pdf"}, "version_id": "80c477e4-c286-4d91-a4d4-47d375d1f105"}, {"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2016-02-17"}], "displaytype": "simple", "download_preview_message": "", "file_order": 1, "filename": "甲1517_本文.pdf", "filesize": [{"value": "7.1 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_11", "mimetype": "application/pdf", "size": 7100000.0, "url": {"label": "本文", "url": "https://ir.soken.ac.jp/record/3144/files/甲1517_本文.pdf"}, "version_id": "58761a60-bfb2-4a31-a4bc-7504c12c6cdc"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "thesis", "resourceuri": "http://purl.org/coar/resource_type/c_46ec"}]}, "item_title": "Range Image Registration Based on Photometry", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Range Image Registration Based on Photometry"}, {"subitem_title": "Range Image Registration Based on Photometry", "subitem_title_language": "en"}]}, "item_type_id": "1", "owner": "21", "path": ["19"], "permalink_uri": "https://ir.soken.ac.jp/records/3144", "pubdate": {"attribute_name": "公開日", "attribute_value": "2012-09-14"}, "publish_date": "2012-09-14", "publish_status": "0", "recid": "3144", "relation": {}, "relation_version_is_last": true, "title": ["Range Image Registration Based on Photometry"], "weko_shared_id": -1}
Range Image Registration Based on Photometry
https://ir.soken.ac.jp/records/3144
https://ir.soken.ac.jp/records/3144666aec21-0f4b-442d-8393-2e39de084399
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
||
![]() |
Item type | 学位論文 / Thesis or Dissertation(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2012-09-14 | |||||
タイトル | ||||||
タイトル | Range Image Registration Based on Photometry | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Range Image Registration Based on Photometry | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_46ec | |||||
資源タイプ | thesis | |||||
著者名 |
THOMAS, Diego
× THOMAS, Diego |
|||||
フリガナ |
トーマス, ディエゴ
× トーマス, ディエゴ |
|||||
著者 |
THOMAS, Diego
× THOMAS, Diego |
|||||
学位授与機関 | ||||||
学位授与機関名 | 総合研究大学院大学 | |||||
学位名 | ||||||
学位名 | 博士(情報学) | |||||
学位記番号 | ||||||
内容記述タイプ | Other | |||||
内容記述 | 総研大甲第1517号 | |||||
研究科 | ||||||
値 | 複合科学研究科 | |||||
専攻 | ||||||
値 | 17 情報学専攻 | |||||
学位授与年月日 | ||||||
学位授与年月日 | 2012-03-23 | |||||
学位授与年度 | ||||||
2011 | ||||||
要旨 | ||||||
内容記述タイプ | Other | |||||
内容記述 | 3D modeling of a real scene stands for constructing a virtual representation of the scene, generally simplified that can be used or modified at our will. Constructing such a 3D model by hand is a laborious and time consuming task, and automating the whole process has attracted growing interest in the computer vision field. In particular, the task of registering (i.e. aligning) different parts of the scene (called range images) acquired from different viewpoints is of crucial importance when constructing 3D models. During the last decades, researchers have concentrated their efforts on this problem and proposed several methodologies to automatically register range images. Thereby, key-point detectors and descriptors have been utilized to match points across different range images using geometric features or textural features. Several similarity metrics have also been proposed to identify the overlapping regions. In spite of the advantages of the current methods, several limitation cases have been reported. In particular, when the scene lacks in discriminative geometric features, the difficulty of accounting for the changes in appearance of the scene observed in different poses, or from different viewpoints, significantly degrades the performance of the current methods. We address this issue by investigating the use of photometry (i.e. the relationship between geometry, reflectance properties and illumination) for range image registration. First, we propose a robust descriptor using albedo that is permissive to errors in the illumination estimation. Second, we propose an albedo extraction technique for specular surfaces that enlarges the range of materials we can deal with. Third, we propose a photometric metric under unknown lighting that allows registration of range images without any assumptions on the illumination. With these proposed methods, we significantly enlarge the practicability and range of applications of range image registration. |
|||||
所蔵 | ||||||
値 | 有 |