ログイン
言語:

WEKO3

  • トップ
  • ランキング
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

  1. 124 情報理工学系研究科
  2. 40 電子情報学専攻
  3. 1244020 博士論文(電子情報学専攻)
  1. 0 資料タイプ別
  2. 20 学位論文
  3. 021 博士論文

Modeling and Recognizing Human Activities from Video

https://doi.org/10.15083/00002422
https://doi.org/10.15083/00002422
0219a987-7a6f-4c54-a132-67cf63009910
名前 / ファイル ライセンス アクション
48057415.pdf 48057415.pdf (4.4 MB)
Item type 学位論文 / Thesis or Dissertation(1)
公開日 2012-03-01
タイトル
タイトル Modeling and Recognizing Human Activities from Video
言語
言語 eng
キーワード
主題Scheme Other
主題 Activity analysis
資源タイプ
資源 http://purl.org/coar/resource_type/c_46ec
タイプ thesis
ID登録
ID登録 10.15083/00002422
ID登録タイプ JaLC
その他のタイトル
その他のタイトル 映像にもとづく人物行動のモデリングと認識
著者 Kitani, Kris Makoto

× Kitani, Kris Makoto

WEKO 6691

Kitani, Kris Makoto

Search repository
著者別名
識別子Scheme WEKO
識別子 6692
姓名 キタニ, クリス マコト
著者所属
著者所属 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 Graduate School of Information Science and Technology Department of Information and Communication Engineering The University of Tokyo
Abstract
内容記述タイプ Abstract
内容記述 This thesis presents a complete computational framework for discovering human actions and modeling human activities from video, to enable intelligent computer systems to effectively recognize human activities. This work is motivated by a desire to create an intelligent computer system that can understand high-level activities of people, thus allowing computer systems to efficiently interact with people. A bottom-up computational framework for learning and modeling human activities is presented in three parts. First, a method for learning primitive actions units is presented. It is shown that by utilizing local motion features and visual context (the appearance of the actor, interactive objects and related background features), the proposed method can effectively discover action categories from a video database without supervision. Second, an algorithm for recovering the basic structure of human activities from a noisy video sequence of actions is presented. The basic structure of an activity is represented by a stochastic context-free grammar, which is obtained by finding the best set of relevant action units in a way that minimizes the description length of a video database of human activities. Experiments with synthetic data examine the validity of the algorithm, while experiments with real data reveals the robustness of the algorithm to action sequences corrupted with action noise. Third, a computational methodology for recognizing human activities from a video sequence of actions is presented. The method uses a Bayesian network, encoded by a stochastic context-free grammar, to parse an input video sequence and compute the posterior probability over all activities. It is shown how the use of deleted interpolation with the posterior probability of activities can be used to recognize overlapping activities. While the theoretical justification and experimental validation of each algorithm is given independently, this work taken as a whole lays the necessary groundwork for designing intelligent systems to automatically learn, model and recognize human activities from a video sequence of actions.
書誌情報 発行日 2008-09-30
日本十進分類法
主題Scheme NDC
主題 548
学位名
学位名 博士(情報理工学)
学位
値 doctoral
学位分野
Information Science and Technology (情報理工学)
学位授与機関
学位授与機関名 University of Tokyo (東京大学)
研究科・専攻
Department of Information and Communication Engineering, Graduate School of Information Science and Technology (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 2008-09-30
学位授与番号
学位授与番号 甲第24186号
学位記番号
博情第205号
戻る
0
views
See details
Views

Versions

Ver.1 2021-03-01 19:59:24.405939
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Cite as

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR 2.0
  • OAI-PMH JPCOAR 1.0
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by WEKO3


Powered by WEKO3