论文信息 - Spatial and Probabilistic Modelling of Pedestrian Behaviour

Spatial and Probabilistic Modelling of Pedestrian Behaviour

This paper investigates the combination of spatial and probabilistic models for reasoning about pedestrian behaviour in visual surveillance systems. Models are learnt by a multi-step unsupervised method and they are used for trajectory labelling and atypical behaviour detection.

Tim J. Ellis | Dimitrios Makris | T. Ellis | Dimitrios Makris

[1] Lawrence R. Rabiner,et al. A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[2] Tim J. Ellis,et al. Finding Paths in Video Sequences , 2001, BMVC.

[3] Luc Van Gool,et al. Modeling and Recognition of Human Actions Using a Stochastic Approach , 2002 .

[4] Svetha Venkatesh,et al. Tracking and Surveillance in Wide-Area Spatial Environments Using the Abstract Hidden Markov Model , 2001, Int. J. Pattern Recognit. Artif. Intell..

[5] Maria Petrou,et al. Properties of the generalised fuzzy aggregation operators , 2001, Pattern Recognit. Lett..

[6] Neil Johnson,et al. Learning object behaviour models , 1998 .

[7] Shaogang Gong,et al. Learning Prior and Observation Augmented Density Models for Behaviour Recognition , 1999, BMVC.

[8] Tim Ellis,et al. Object detection and tracking in an open and dynamic world , 2001 .