Robust tracking of persons in real-world environments and in real-time is a common goal in many video applications. In this paper a computational system for the real-time tracking of multiple persons in natural environments is presented. The system integrates state-of-the-art methodologies for the analysis of movement and color, as well as for the detection of faces. Face detection is complemented by a face tracking module based on heuristics developed by the authors. Exemplary results of the integrated system working in real-world video sequences are shown.