Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model
- 1 June 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel principal component analysis (KPCA) based feature extraction and factorial conditional random field (FCRF) based motion modeling. Silhouette data is represented more compactly by nonlinear dimensionality reduction that explores the underlying structure of the articulated action space and preserves explicit temporal orders in projection trajectories of motions. FCRF models temporal sequences in multiple interacting ways, thus increasing joint accuracy by information sharing, with the ideal advantages of discriminative models over generative ones (e.g., relaxing independence assumption between observations and the ability to effectively incorporate both overlapping features and long-range dependencies). The experimental results on two recent datasets have shown that the proposed framework can not only accurately recognize human activities with temporal, intra-and inter-person variations, but also is considerably robust to noise and other factors such as partial occlusion and irregularities in motion styles.Keywords
This publication has 15 references indexed in Scilit:
- Learning and Detecting Activities from Movement Trajectories Using the Hierarchical Hidden Markov ModelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Inferring 3D body pose from silhouettes using activity manifold learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Dynamic conditional random fieldsPublished by Association for Computing Machinery (ACM) ,2004
- Generative modeling for continuous non-linearly embedded visual inferencePublished by Association for Computing Machinery (ACM) ,2004
- A kernel view of the dimensionality reduction of manifoldsPublished by Association for Computing Machinery (ACM) ,2004
- Human motion analysis: a reviewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The recognition of human movement using temporal templatesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- A Global Geometric Framework for Nonlinear Dimensionality ReductionScience, 2000
- Nonlinear Component Analysis as a Kernel Eigenvalue ProblemNeural Computation, 1998