Multi-scale f-formation discovery for group detection

Francesco Setti, Oswald Lanz, Roberta Ferrario, Vittorio Murino, Marco CristaniICIP 2013 · OpenReview

Abstract

We present an unsupervised approach for the automatic detection of static interactive groups. The approach builds upon a novel multi-scale Hough voting policy, which incorporates in a flexible way the sociological notion of group as F-formation; the goal is to model at the same time small arrangements of close friends and aggregations of many individuals spread over a large area. Our technique is based on a competition of different voting sessions, each one specialized for a particular group cardinality; all the votes are then evaluated using information theoretic criteria, producing the final set of groups. The proposed technique has been applied on public benchmark sequences and a novel cocktail party dataset, evaluating new group detection metrics and obtaining state-of-the-art performances.
BibTeX
@inproceedings{setti2013multi,
  author = {Francesco Setti and Oswald Lanz and Roberta Ferrario and Vittorio Murino and Marco Cristani},
  title = {{Multi-scale f-formation discovery for group detection}},
  booktitle = {ICIP},
  year = {2013},
  url = {https://openreview.net/forum?id=yGYV_ecxPxH},
}

Loading related content...

Figure