Abstract

Social activity based on body motion is a key feature for non-verbal and physical behavior defined as function for communicative signal and social interaction between individuals. Social activity recognition is important to study human-human communication and also human-robot interaction. Based on that, this research has threefold goals: (1) recognition of social behavior (e.g. human-human interaction) using a probabilistic approach that merges spatio-temporal features from individual bodies and social features from the relationship between two individuals; (2) learn priors based on physical proximity between individuals during an interaction using proxemics theory to feed a probabilistic ensemble of classifiers; and (3) provide a public dataset with RGB-D data
of social daily activities including risk situations useful to test approaches for assisted living, since this type of dataset is still missing. Results show that using a modified dynamic Bayesian mixture model designed to merge features with different semantics and also with proximity priors, the proposed framework can correctly recognize social activities in different situations, e.g. using data from one or two individuals.