In this paper, a novel approach for tracking extended objects is presented. The target object is modeled as a circular disc such that the center and extent of the target object can be estimated. At each time step, a finite set of position measurements that are corrupted with stochastic noise may be available. Each position measurement stems from an unknown measurement source on the extended object. In contrast to existing approaches, no statistical assumptions about the distribution of the measurement sources on the extended object are made. As a consequence, it is necessary to deal with stochastic and set-valued uncertainties. For this purpose, a novel combined stochastic and set-theoretic estimator that employs random hyperboloids to express the uncertainties about the true circular disc is derived.