Acoustic source localization and discrimination in urban environments
Manish Kushwaha, Xenofon Koutsoukos, Péter Völgyesi, Ákos Lédeczi · 2009
Abstract – Collaborative localization and discrimina-tion of acoustic sources is an important problem for monitoring urban environments. Acoustic source local-ization typically is performed using either signal-based approaches that rely on transmission of raw acoustic data and are not suitable for resource-constrained wire-less sensor networks or feature-based methods that re-sult in degraded accuracy, especially for multiple tar-gets. In this paper, we present a feature-based localiza-tion and discrimination approach for multiple acoustic sources using wireless sensor networks that fuses beam-form and power spectral density data from each sensor. Our approach utilizes a graphical model for estimating the position of the sources as well as their fundamen-tal and dominant harmonic frequencies. We present simulation and experimental results that show improve-ment in the localization accuracy and target discrim-ination. Our experimental results are obtained using motes equipped with microphone arrays and an onboard FPGA for computing the beamform and the power spec-tral density.1.