Detecting small group activities from multimodal observations

Abstract

This article addresses the problem of detecting configurations and activities of small groups of people in an augmented environment. The proposed approach takes a continuous stream of observations coming from different sensors in the environment as input. The goal is to separate distinct distributions of these observations corresponding to distinct group configurations and activities. This article describes an unsupervised method based on the calculation of the Jeffrey divergence between histograms over observations. These histograms are generated from adjacent windows of variable size slid from the beginning to the end of a meeting recording.The peaks of the resulting Jeffrey divergence curves are detected using successive robust mean estimation. After a merging and filtering process, the retained peaks are used to select the best model, i.e. the best allocation of observation distributions for a meeting recording.These distinct distributions can be interpreted as distinct segments of group configuration and activity. To evaluate this approach, 5 small group meetings, one seminar and one cocktail party meeting have been recorded. The observations of the small groups meetings and the seminar were generated by a speech activity detector, while the observations of the cocktail party meeting were generated by both the speech activity detector and a visual tracking system. The authors measured the correspondence between detected segments and labeled group configurations and activities. The obtained results are promising, in particular as the method is completely unsupervised.

Group affiliation detection using model divergence for wearable devices

“…Brdiczka et al [5] recognized changes in group configurations by calculating the Jeffrey's divergence over histograms of multi-modal sensor data. There divergence indicates differences between group configurations, where here we investigate divergence as indicator of pair-wise group affinity.…”

“…Each node n i in the set of all nodes with dimension N can now calculate their disparity to neighboring nodes based on the Jeffrey's divergence. The Jeffrey's divergence is an extension of the Kullback-Leibler divergence, selected because it is numerically stable and symmetric [5]. The Jeffrey's divergence D j between two distributions P and Q is given by:…”

Designing heterogeneous distributed GAs by efficiently self-adapting the migration period

“…Clustering analysis, used in many disciplines and applications [10,35], is an important tool and a descriptive task seeking to identify homogeneous groups of objects based on the values of their attributes. The problem of cluster analysis can be modelled as a maximum cut problem [18].…”

Automatic characterization of emergent phenomena in complex systems

“…But since organization may be seen as the result of an interaction dynamics between lower-level entities, and between these entities and their environment, one can think of studying the construction of these organizations by studying the dynamics of the underlying interaction networks. In social sciences, there is a long tradition of studying human communities, using interaction networks as a tool of choice [24][25][26][27][28]. This enables the detection of the emergence of groups based on the density of connections between the individuals.…”