Behavioural Analysis with Movement Cluster Model for Concurrent Actions

We present an approach to model articulated human movements and to analyse their behavioural semantics. First, we describe a novel dynamic and behavioural model that uses movements, a sequence of consecutive poses, from motion captured video data to establish priors for both tracking and behavioural analysis. Second, using that model, we show how we can both learn and subsequently recognise human activity. Activities are modelled and recognised independently to allow concurrent and complex actions. Finally, we combine activity recognition with tracking to produce an overall evaluation of the effectiveness of the approach using publicly available datasets.