Fast and Accurate Frequency Estimation Using Sliding DFT

TL;DR

This paper introduces a fast, stable, and accurate frequency estimation method using the Sliding DFT, outperforming existing estimators in stability and performance for large N.

Contribution

A novel frequency estimator leveraging the stable Sliding DFT with an added correction term, improving accuracy and computational efficiency over prior methods.

Findings

Outperforms Jacobsen's and Candan's estimators in simulations

Provides stable and efficient frequency estimation for large N

Achieves better accuracy with the proposed correction term

Abstract

Frequency Estimation of a complex exponential is a problem relevant to a large number of fields. In this paper a computationally efficient and accurate frequency estimator is presented using the guaranteed stable Sliding DFT which gives stability as well as computational efficiency. The estimator approaches Jacobsen's estimator and Candan's estimator for large N with an extra correction term multiplied to it for the stabilization of the sliding DFT. Simulation results show that the performance of the proposed estimator were found to be better than Jacobsen's estimator and Candan's estimator.