WEKO3
アイテム
{"_buckets": {"deposit": "353f098a-4ff3-48b8-a0bd-a30c29f938e3"}, "_deposit": {"id": "3444", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "3444"}, "status": "published"}, "_oai": {"id": "oai:repository.dl.itc.u-tokyo.ac.jp:00003444", "sets": ["234", "262"]}, "item_7_alternative_title_1": {"attribute_name": "その他のタイトル", "attribute_value_mlt": [{"subitem_alternative_title": "環境への自動適応を伴う低解像度画像からの頭部姿勢推定"}]}, "item_7_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2012-03-22", "bibliographicIssueDateType": "Issued"}, "bibliographic_titles": [{}]}]}, "item_7_date_granted_25": {"attribute_name": "学位授与年月日", "attribute_value_mlt": [{"subitem_dategranted": "2012-03-22"}]}, "item_7_degree_name_20": {"attribute_name": "学位名", "attribute_value_mlt": [{"subitem_degreename": "修士(情報理工学)"}]}, "item_7_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Head pose estimation technique is a core of many computer vision applications. Head pose estimation is often used as cues to estimate human attention. Due to limitations such as camera placement location or system resources, it is not always appropriate to install high resolution cameras on every system. Head pose estimation from low resolution images are desired in such situation. Although many methods have been proposed for head pose estimation from low resolution images, there are many technical limitations for the implementation of the system. To construct an effective head pose estimation system, a large number of head pose training samples collected from the same environment as test environment are desired because the process of acquiring such dataset is extremely time-consuming and makes it impossible to prepare scene-specific dataset for every scene. The first part of this paper describes the method to automatically obtain scene-specific dataset. This method exploits the observation that people are more likely to to turn their head to where they are walking. With this observation, the tracking method is applied to the video taken from the scene beforehand. Head pose training data are then inferred from tracking results and are acquired automatically. This method enables automatic acquisition of training data and solves the problem of data collection. The second part describes the method to improve head pose estimation in scenes with short available videos or low number of walking pedestrians so adequate amount of head pose samples cannot be captured. Datasets captured from various scenes are used to alleviate the problem and increase the accuracy significantly. The third part describes the method which improves head pose estimation accuracy for scenes with dramatic difference within the scene. This method adaptively divides scenes into multiple parts in order to localize head pose estimator.", "subitem_description_type": "Abstract"}]}, "item_7_full_name_3": {"attribute_name": "著者別名", "attribute_value_mlt": [{"nameIdentifiers": [{"nameIdentifier": "8263", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "ジャムウェイハー, イサラン"}]}]}, "item_7_select_21": {"attribute_name": "学位", "attribute_value_mlt": [{"subitem_select_item": "master"}]}, "item_7_subject_13": {"attribute_name": "日本十進分類法", "attribute_value_mlt": [{"subitem_subject": "547", "subitem_subject_scheme": "NDC"}]}, "item_7_text_24": {"attribute_name": "研究科・専攻", "attribute_value_mlt": [{"subitem_text_value": "情報理工学系研究科電子情報学専攻"}]}, "item_7_text_36": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"subitem_text_value": "Thesis"}]}, "item_7_text_4": {"attribute_name": "著者所属", "attribute_value_mlt": [{"subitem_text_value": "東京大学大学院情報理工学系研究科電子情報学専攻"}, {"subitem_text_value": "Department of Information and Communication Engineering, Graduate School of Information Science and Technology, The University of Tokyo"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Chamveha, Isarun"}], "nameIdentifiers": [{"nameIdentifier": "8262", "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": "2017-05-31"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "48106416.pdf", "filesize": [{"value": "11.7 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 11700000.0, "url": {"label": "48106416.pdf", "url": "https://repository.dl.itc.u-tokyo.ac.jp/record/3444/files/48106416.pdf"}, "version_id": "24ed92bc-8806-4dcd-b428-d453ef6d38f9"}]}, "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": "Head Pose Estimation from Low Resolution Image with Scene Adaptation", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Head Pose Estimation from Low Resolution Image with Scene Adaptation"}]}, "item_type_id": "7", "owner": "1", "path": ["234", "262"], "permalink_uri": "http://hdl.handle.net/2261/52235", "pubdate": {"attribute_name": "公開日", "attribute_value": "2012-10-01"}, "publish_date": "2012-10-01", "publish_status": "0", "recid": "3444", "relation": {}, "relation_version_is_last": true, "title": ["Head Pose Estimation from Low Resolution Image with Scene Adaptation"], "weko_shared_id": null}
Head Pose Estimation from Low Resolution Image with Scene Adaptation
http://hdl.handle.net/2261/52235
http://hdl.handle.net/2261/52235a8e7dbd5-112f-4319-9a5b-0203903e87da
名前 / ファイル | ライセンス | アクション |
---|---|---|
48106416.pdf (11.7 MB)
|
|
Item type | 学位論文 / Thesis or Dissertation(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2012-10-01 | |||||
タイトル | ||||||
タイトル | Head Pose Estimation from Low Resolution Image with Scene Adaptation | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源 | http://purl.org/coar/resource_type/c_46ec | |||||
タイプ | thesis | |||||
その他のタイトル | ||||||
その他のタイトル | 環境への自動適応を伴う低解像度画像からの頭部姿勢推定 | |||||
著者 |
Chamveha, Isarun
× Chamveha, Isarun |
|||||
著者別名 | ||||||
識別子 | 8263 | |||||
識別子Scheme | WEKO | |||||
姓名 | ジャムウェイハー, イサラン | |||||
著者所属 | ||||||
著者所属 | 東京大学大学院情報理工学系研究科電子情報学専攻 | |||||
著者所属 | ||||||
著者所属 | Department of Information and Communication Engineering, Graduate School of Information Science and Technology, The University of Tokyo | |||||
Abstract | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Head pose estimation technique is a core of many computer vision applications. Head pose estimation is often used as cues to estimate human attention. Due to limitations such as camera placement location or system resources, it is not always appropriate to install high resolution cameras on every system. Head pose estimation from low resolution images are desired in such situation. Although many methods have been proposed for head pose estimation from low resolution images, there are many technical limitations for the implementation of the system. To construct an effective head pose estimation system, a large number of head pose training samples collected from the same environment as test environment are desired because the process of acquiring such dataset is extremely time-consuming and makes it impossible to prepare scene-specific dataset for every scene. The first part of this paper describes the method to automatically obtain scene-specific dataset. This method exploits the observation that people are more likely to to turn their head to where they are walking. With this observation, the tracking method is applied to the video taken from the scene beforehand. Head pose training data are then inferred from tracking results and are acquired automatically. This method enables automatic acquisition of training data and solves the problem of data collection. The second part describes the method to improve head pose estimation in scenes with short available videos or low number of walking pedestrians so adequate amount of head pose samples cannot be captured. Datasets captured from various scenes are used to alleviate the problem and increase the accuracy significantly. The third part describes the method which improves head pose estimation accuracy for scenes with dramatic difference within the scene. This method adaptively divides scenes into multiple parts in order to localize head pose estimator. | |||||
書誌情報 | 発行日 2012-03-22 | |||||
日本十進分類法 | ||||||
主題 | 547 | |||||
主題Scheme | NDC | |||||
学位名 | ||||||
学位名 | 修士(情報理工学) | |||||
学位 | ||||||
値 | master | |||||
研究科・専攻 | ||||||
情報理工学系研究科電子情報学専攻 | ||||||
学位授与年月日 | ||||||
学位授与年月日 | 2012-03-22 |