Abstract | ||
---|---|---|
Recognition of human behaviours requires modeling the underlying spatial and temporal structures of their motion patterns. Such structures are intrinsi- cally probabilistic and therefore should be modelled as stochastic processes. In this paper we introduce a framework to recognise behaviours based on both learning prior and continuous propagation of density models of behaviour patterns. Prior is learned from training sequences using hidden Markov mod- els and density models are augmented by current visual observation. |
Year | Venue | Keywords |
---|---|---|
1999 | BMVC | stochastic process,human behaviour |
Field | DocType | Citations |
Visual observation,Computer vision,Computer science,Stochastic process,Artificial intelligence,Probabilistic logic,Hidden Markov model,Machine learning | Conference | 11 |
PageRank | References | Authors |
1.78 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Walter | 1 | 111 | 10.36 |
Alexandra Psarrou | 2 | 199 | 27.14 |
Shaogang Gong | 3 | 7941 | 498.04 |