A Probabilistic Framework for Recognizing Similar Actions using Spatio-Temporal Features

One of the challenges found in recent methods for action recognition has been to classify ambiguous actions successfully . In the case of methods that use spatio-temporal features this phenomenon is observed when two actions generate similar feature types. Ideally, a probabilistic c lassification method would be based on a model of the full joint distribution of features, but this is computationally intractable. In this paper we propose using an approximation of the full joint via first order dependencies between fe ature types using so-called Chow-Liu trees. We obtain promising results and achieve an improvement in the classification accuracy over naive Bayes an d other simple classifiers. Our implementation of the method makes use of a b inary descriptor for a video analogous to one previously used in location recognition for mobile robots. Because of the simplicity of the algorithm, once the offline learning phase is over, real-time action recognition is pos sible and we present an adaptation of this method that works in real-time.