In this paper, we present two new observation models based on optical flow information to track objects using particle filter algorithms. Although optical flow information enabl...
Abstract--Fingerprinting operators generate functional signatures of game players and are useful for their automated analysis independent of representation or encoding. The theory ...
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-s...
We propose a novel Active Volume Model (AVM) which deforms in a free-form manner to minimize energy. Unlike Snakes and level-set active contours which only consider curves or surfa...
— This paper presents a general framework for multi-sensor object recognition through a discriminative probabilistic approach modelling spatial and temporal correlations. The alg...