Online source number estimation based on sequential hypothesis test and subspace tracking

Abstract

We investigated the problem of source enumeration in array signal processing. The conventional batch estimating methods do not yield satisfactory tracking performance in a dynamic environment. In order to solve this problem, an online source number estimation method is proposed in this paper. The developed algorithm exploits subspace tracking and hypothesis test to update the estimation of the signal number sequentially. Simulation results validate the superiority of the new method in terms of tracking capacity and computation efficiency.

https://ift.tt/2IFBvrB