20 search results - page 1 / 4 » Learning Semantic Scene Models by Object Classification and ... |
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
The visual surveillance task is to monitor the activity of objects in a scene. In far-field settings (i.e., wide outdoor areas), the majority of visible activities are objects movi...
ECCV
2006
Springer
13 years 8 months ago
2006
Springer
Abstract. In this paper, we describe an unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from longterm observations of mo...
SPIEVIP
2010
13 years 7 months ago
2010
In video surveillance, automatic methods for scene understanding and activity modeling can exploit the high redundancy of object trajectories observed over a long period of time. ...
CVPR
2011
IEEE
12 years 12 months ago
2011
IEEE
In this paper, a Random Field Topic (RFT) model is proposed for semantic region analysis from motions of objects in crowded scenes. Different from existing approaches of learning ...
CVPR
2008
IEEE
14 years 6 months ago
2008
IEEE
We propose a novel nonparametric Bayesian model, Dual Hierarchical Dirichlet Processes (Dual-HDP), for trajectory analysis and semantic region modeling in surveillance settings, i...