In our society, video processing has become a convenient and widely used tool to assist, protect and simplify the daily life of people in areas such as surveillance and video conferencing. The growing number of cameras, the handling and analysis of these vast amounts of video data enable the development of multi-camera applications that cooperatively use multiple sensors. In many applications, bandwidth constraints, privacy issues, and difficulties in storing and analyzing large amounts of video data make applications costly and technically challenging. In this thesis, we deploy techniques ranging from low-level to high-level approaches, specifically designed for multi-camera networks. As a low-level approach, we designed a novel low-level foreground detection algorithm for real-time tracking applications, concentrating on difficult and changing illumination conditions. The main part of this dissertation focuses on a detailed analysis of two novel state-of-the-art real-time tracking approaches: a multi-camera tracking approach based on occupancy maps and a distributed multi-camera tracking approach with a feedback loop. As a high-level application we propose an approach to understand the dynamics in meetings - so called, smart meetings - using a multi-camera setup, consisting of fixed ambient and portable close-up cameras. For all method, we provided qualitative and quantitative results on several experiments, compared to state-of-the-art methods.