WEKO3
アイテム
Modeling and Recognizing Human Activities from Video
https://doi.org/10.15083/00002422
https://doi.org/10.15083/000024220219a987-7a6f-4c54-a132-67cf63009910
名前 / ファイル | ライセンス | アクション |
---|---|---|
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 | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_46ec | |||||
資源タイプ | 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 |
|||||
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 | ||||||
値 | 大学院情報理工学系研究科電子情報学専攻 | |||||
著者所属 | ||||||
値 | 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 | ||||||
値 | 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 | ||||||
値 | 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 | ||||||
値 | 博情第205号 |