Abstract
Sparse arrays, such as minimum redundancy arrays and coprime arrays, often exploit the second-order statistics of the propagating field to localize more sources than sensors by constructing an augmented covariance matrix (ACM) from the estimated spatial correlation. The source localization performance largely depends on the number of snapshots available, which might be limited in many acoustical environments due to the propagation speed, large array aperture, and non-stationary field. This paper proposes a new approach for wideband source enumeration and direction-of-arrival (DOA) estimation on any sparse array geometry. The proposed algorithm decomposes the wideband signals into multiple disjoint frequency bands, computes the narrowband spatial periodograms and averages them to reinforce the sources’ spatial spectral information. The spatial correlation estimated from the wideband periodogram populates the diagonals of a Hermitian Toeplitz ACM. This ACM then goes through eigenvalue decomposition, where its eigenvalues are employed for source enumeration through a new information based criterion and its eigenvectors for DOA estimation through the MUSIC algorithm. Simulations show that the proposed algorithm achieves improved performance enumerating and estimating DOAs for more wideband sources than sensors in low snapshot scenarios when compared to existing approaches. [Work supported by ONR grant N00014-13-1-0230.]