Modeling and Recognizing Human Activities from Video
スポンサーリンク
概要
- 論文の詳細を見る
This paper 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. 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.
- 一般社団法人情報処理学会の論文
- 2009-06-02
著者
-
Sato Yoichi
The University of Tokyo
-
Yoichi Sato
The University of Tokyo
-
Yoichi Sato
University of Tokyo
-
Sato Yoichi
University Of Tokyo
関連論文
- Image Enhancement of Low-light Scenes with Near-infrared Flash Images
- Video Segmentation with Motion Smoothness
- Image Enhancement of Low-light Scenes with Near-infrared Flash Images
- Manifold-based photometric stereo with cast shadows (コンピュータビジョンとイメージメディア)
- Manifold-based photometric stereo with cast shadows (パターン認識・メディア理解)
- Manifold-based photometric stereo with cast shadows (画像工学)
- Reconstruction an object's shape from its appearance manifold under moving light (コンピュータビジョンとイメージメディア)
- Tracking People in Crowds by Feature Point Cluster Analysis Based on Spatial and Frequency Domain Cues
- Aesthetic Quality Classification of Photographs
- 環境への自動適応を伴うアピアランスベース頭部姿勢推定
- 環境への自動適応を伴うアピアランスベース頭部姿勢推定
- Automatic Radiometric Calibration in Photometric Stereo by Using Irradiance Consistency
- Automatic Radiometric Calibration in Photometric Stereo by Using Irradiance Consistency
- Joint Estimation of Facial Pose and Expression Using Variable-Intensity Templates
- Joint Estimation of Facial Pose and Expression Using Variable-Intensity Templates
- Modeling and Recognizing Human Activities from Video
- Modeling and Recognizing Human Activities from Video