Instantaneous Frequency Estimation Using Sequential Bayesian Techniques

The online estimation of the instantaneous frequency (IF) of time-varying (TV) signals with highly nonlinear phase functions is a challenging problem. In this paper, we propose an IF estimation method using Bayesian techniques, which combines particle filtering and Markov Chain Monte Carlo (MCMC) methods, to sequentially estimate highly nonlinear TV frequency variations as piecewise linear functions. Simultaneously applying parameter estimation and model selection, the new technique is extended to the IF estimation of multicomponent signals. Using simulations, we demonstrate the performance of our approach for different signals and environments.