Recognition of Group Activities using Dynamic Probabilistic Networks

13 years 8 months ago
Recognition of Group Activities using Dynamic Probabilistic Networks
Dynamic Probabilistic Networks (DPNs) are exploited for modelling the temporal relationships among a set of different object temporal events in the scene for a coherent and robust scene-level behaviour interpretation. In particular, we develop a Dynamically Multi-Linked Hidden Markov Model (DML-HMM) to interpret group activities involving multiple objects captured in an outdoor scene. The model is based on the discovery of salient dynamic interlinks among multiple temporal events using DPNs. Object temporal events are detected and labelled using Gaussian Mixture Models with automatic model order selection. A DMLHMM is built using Schwarz's Bayesian Information Criterion based factorisation resulting in its topology being intrinsically determined by the underlying causality and temporal order among different object events. Our experiments demonstrate that its performance on modelling group activities in a noisy outdoor scene is superior compared to that of a Multi-Observation Hidd...
Shaogang Gong, Tao Xiang
Added 15 Oct 2009
Updated 31 Oct 2009
Type Conference
Year 2003
Where ICCV
Authors Shaogang Gong, Tao Xiang
Comments (0)