Direction of Arrival Estimation for Multiple Source Tracking (MUST) in Industrial Environments
Acoustic localization and analysis of multiple industrial sound sources such as motors, pumps etc., are challenging as their frequency content is largely time invariant and emissions of similar machines are highly correlated. Therefore, standard assumptions for localization, taken e.g., in DUET, such as disjoint time-frequency content of the sources do not hold. In this talk we will present a Bayesian multiple source tracking (MUST) algorithm that can estimate and track the direction of multiple, possibly correlated, wideband sources. MUST approximates the posterior probability density function of the source directions in time-frequency domain with a particle filter. In contrast to other previous algorithms, no time-averaging is necessary, therefore moving sources can be tracked. MUST uses a new low complexity weighting and regularization scheme to fuse information from different frequencies and to overcome the problem of overfitting when few sensors are available.