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.

• Type: Conference
• Year: 2002
• Where: BMVC
• Authors: Dimitrios Makris, Tim Ellis
• Keywords: Atypical Behaviour Detection, BMVC 2002, Computer Vision, Multi-step Unsupervised Method, Pedestrian Behaviour