『徳島大学 教育・研究者情報データベース (EDB)』---[学外] /
ID: Pass:

登録内容 (EID=243551)

EID=243551EID:243551, Map:0, LastModified:2018年1月16日(火) 14:39:41, Operator:[三好 小文], Avail:TRUE, Censor:0, Owner:[任 福継], Read:継承, Write:継承, Delete:継承.
種別 (必須): 国際会議 [継承]
言語 (必須): 英語 [継承]
招待 (推奨):
審査 (推奨): Peer Review [継承]
カテゴリ (推奨): 研究 [継承]
共著種別 (推奨): 国際共著 (徳島大学内研究者と国外研究機関所属研究者との共同研究) [継承]
学究種別 (推奨): 博士後期課程学生による研究報告 [継承]
組織 (推奨): 1.徳島大学.大学院ソシオテクノサイエンス研究部.情報ソリューション部門.感性情報処理 (2006年4月1日〜2016年3月31日) [継承]
著者 (必須): 1. (英) Ma, Jia (日) (読)
役割 (任意):
貢献度 (任意):
学籍番号 (推奨):
[継承]
2.任 福継 ([徳島大学.大学院社会産業理工学研究部.理工学域.知能情報系.情報工学分野]/[徳島大学.理工学部.理工学科.情報光システムコース.情報工学講座]/->個人[中川 福継])
役割 (任意):
貢献度 (任意):
学籍番号 (推奨):
[継承]
題名 (必須): (英) DETECT AND TRACK THE DYNAMIC DEFORMATION HUMAN BODY WITH THE ACTIVE SHAPE MODEL MODIFIED BY MOTION VECTORS  (日)    [継承]
副題 (任意):
要約 (任意): (英) At present, many systems are being used in the detection of human body from video, especially the moving human body. These systems usually recognize the human body features, such as learning the human body features by training, recognition of the skin color or body shape, and identify the specifically movement of human body. These methods have some problems. The training methods require a lot of training data, but only identify specific targets. The methods of identify the shape of human body and skin color are a great influenced by the video quality and content. The methods of detecting motion features are often complex and greatly relied to the 3D data. In this study, we propose an Active Shape Model (ASM) modified by the motion vectors to detect and track the deformed human body for action. Active shape model is used to identify the particular shapes; it is also a training method. We use kinds of original human body model modified by motion vectors, instead of training result. Thus the active shape model can detect the human body after deformation. So that human body won't be lost or repeated detected. In this method, we use Optical-flow method to get the motion vectors. The function of the method is conformed by experiment and the detecting success rate of moving human body is 94%. The experimental results and discussion are also presented.  (日)    [継承]
キーワード (推奨):
発行所 (推奨): IEEE [継承]
誌名 (必須): (英) Proc. of IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS 2011) (日) (読)
ISSN (任意):
[継承]
(必須): [継承]
(必須): [継承]
(必須): 587 591 [継承]
都市 (必須): 北京 (Beijing/[中華人民共和国]) [継承]
年月日 (必須): 西暦 2011年 9月 16日 (平成 23年 9月 16日) [継承]
URL (任意):
DOI (任意): 10.1109/CCIS.2011.6045137    (→Scopusで検索) [継承]
PMID (任意):
NAID (任意):
WOS (任意):
Scopus (任意): 2-s2.0-80055101511 [継承]
評価値 (任意):
被引用数 (任意):
指導教員 (推奨):
備考 (任意):

標準的な表示

和文冊子 ● Jia Ma and Fuji Ren : DETECT AND TRACK THE DYNAMIC DEFORMATION HUMAN BODY WITH THE ACTIVE SHAPE MODEL MODIFIED BY MOTION VECTORS, Proc. of IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS 2011), 587-591, Beijing, Sep. 2011.
欧文冊子 ● Jia Ma and Fuji Ren : DETECT AND TRACK THE DYNAMIC DEFORMATION HUMAN BODY WITH THE ACTIVE SHAPE MODEL MODIFIED BY MOTION VECTORS, Proc. of IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS 2011), 587-591, Beijing, Sep. 2011.

関連情報

Number of session users = 1, LA = 0.45, Max(EID) = 383956, Max(EOID) = 1027010.