A Bayesian Network for the Classification of Human Motion as Observed by Distributed Radar

Peter Svenningsson, Francesco Fioranelli, Alexander Yarovoy, Anthony F. Martone

Research output: Contribution to journalArticleScientificpeer-review


In this paper, a statistical model of human motion as observed by a network of radar sensors is presented where knowledge on the position and heading of the target provides information on the observation conditions of each sensor node. Sequences of motions are estimated from measurements of instantaneous Doppler frequency, which captures informative micro-motions exhibited by the human target. A closed-form Bayesian estimation algorithm is presented that jointly estimates the state of the target and its exhibited motion class which are described by a hidden Markov model. To correct errors in the estimated motion class distribution introduced by faulty modeling assumptions, calibration of the probability distribution and measurement likelihood is performed by isotonic regression. It is shown, by modeling sensor observation conditions and by isotonic calibration of the measurement likelihood, that a cognitive resource management system is able to increase classification accuracy by 5-10 % while utilizing sensor resources in accordance with defined mission objectives.

Original languageEnglish
Article number9780548
JournalIEEE Transactions on Aerospace and Electronic Systems
Publication statusE-pub ahead of print - 2022


  • cognitive radar
  • dynamic Bayesian network
  • micro-Doppler signature
  • radar network
  • radar resource management
  • radar target classification


Dive into the research topics of 'A Bayesian Network for the Classification of Human Motion as Observed by Distributed Radar'. Together they form a unique fingerprint.

Cite this