The authors report on their development of a new and efficient framework for group activity analysis, using social signaling cues to describe the degree of interaction.
This paper presents a novel and efficient framework for group activity analysis. People in a scene can be intuitively represented by an undirected graph where vertices are people and the edges between two people are weighted by how much they are interacting. Social signaling cues are used to describe the degree of interaction between people. We propose a graph-based clustering algorithm to discover interacting groups in crowded scenes. Two social signaling cues are presented and compared for group discovery. The grouping of people in the scene serves to isolate the groups engaged in the dominant activity, effectively eliminating dataset contamination. Using discovered interacting groups, the authors create a descriptor capturing the motion and interaction of people within it. A bag-of-words approach is used to represent group activity and a SVM classifier is used for activity recognition. The proposed framework is evaluated in its ability to discover interacting groups and perform group activity recognition using two public datasets. The overall recognition system is compared to a baseline top-down model to understand the impact of social cues for activity recognition. The results of both the steps show that the authors’ method outperforms state-of-the-art methods for group discovery and achieves recognition rates comparable to state-of-the-art methods for group activity recognition. (Published Abstract Provided)