Abstract
We consider the problem of data association in a multi- person tracking context. In semi-crowded environments, people are still discernible as individually moving entities, that undergo many interac- tions with other people in their direct surrounding. Finding the correct association is therefore difficult, but higher-order social factors, such as group membership, are expected to ease the problem. However, estimat- ing group membership is a chicken-and-egg problem: knowing pedestrian tra jectories, it is rather easy to find out possible groupings in the data, but in crowded scenes, it is often difficult to estimate closely interacting tra jectories without further knowledge about groups. To this end, we propose a third-order graphical model that is able to jointly estimate correct tra jectories and group memberships over a short time window. A set of experiments on challenging data underline the importance of joint reasoning for data association in crowded scenarios.