Microphone array based classification for security monitoring in unstructured environments

The aim of this paper is to describe a novel security system able to localize and classify audio sources in an outdoor environment. Its primary intended use is for security monitoring in severe scenarios, and it has been designed to cope with a large set of heterogeneous objects, including weapons, human speakers and vehicles. The system is the result of a research project sponsored by the Italian Ministry of Defense. It is composed of a large squared array of 864 microphones arranged in a rectangular lattice, whose input is processed using a classical delay-and-sum beamformer. The result of this localization process is elaborated by a complex multi-level classification system designed in a modular fashion. In this paper, after presenting the details of the system's design, with a particular emphasis on the innovative aspects that are introduced with respect to the state-of-the-art, we provide an extensive set of simulations showing the effectiveness of the proposed architecture. We conclude by describing the current limits of the system, and the projected further developments.