We present an online method to estimate the number of radar emitters from sequential batches of detected pulses. To do this, we employ a recently developed Bayesian nonparametric clustering method that automatically infers the number of clusters in the data. Semiparametric change detection ensures accurate cardinality estimates in a dynamic signal environment where the number of emitters changes over time. This method improves upon the state of the art by providing better estimates of the number of clusters while processing pulses in an online fashion. We demonstrate its effectiveness on three simulated radar scenarios with increasing pulse density.
Online Estimation of Radar Emitter Cardinality via Bayesian Nonparametric Clustering
IEEE Transactions on Aerospace and Electronic Systems ; 57 , 6 ; 3791-3800
2021-12-01
1305027 byte
Article (Journal)
Electronic Resource
English
An incremental nonparametric Bayesian clustering-based traversable region detection method
British Library Online Contents | 2017
|Nonparametric Bayesian Image Segmentation
British Library Online Contents | 2008
|An Online Multisensor Data Fusion Framework for Radar Emitter Classification
DOAJ | 2016
|