Skip to main navigation Skip to search Skip to main content

Fading unscented–extended kalman filter for multiple targets tracking with symmetric equations of nonlinear measurements

  • Cui Zhang*
  • , Yingmin Jia
  • , Changqing Chen
  • *Corresponding author for this work
  • Beihang University
  • CAS - Beijing Institute of Control Engineering

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper is devoted to the problem of multiple targets tracking based on symmetric equations of nonlinear measurements. We develop a nonlinear stochastic model with unknown random bias to provide a unified structure for the tracking systems with different types of symmetric measurement equations. Moreover, the fading unscented–extended Kalman filter (FUEF) is designed to deal with the strong nonlinearities by embedding the unscented transforminto the extended Kalman filter and to conduct the effect of unknown bias by inserting the fading factor. The performance of the novel filter paired with two of symmetric measurement equations are illustrated and compared by the Monte Carlo simulation results.

Original languageEnglish
Title of host publicationProceedings of 2016 Chinese Intelligent Systems Conference
EditorsWeicun Zhang, Yingmin Jia, Hongbo Li, Junping Du
PublisherSpringer Verlag
Pages37-49
Number of pages13
ISBN (Print)9789811023347
DOIs
StatePublished - 2016
EventInternational Conference on Chinese Intelligent Systems Conference, CISC 2016 - Xiamen, China
Duration: 1 Jan 2016 → …

Publication series

NameLecture Notes in Electrical Engineering
Volume405
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Chinese Intelligent Systems Conference, CISC 2016
Country/TerritoryChina
CityXiamen
Period1/01/16 → …

Keywords

  • Kalman filter
  • Multiple targets tracking
  • Nonlinear system
  • Random bias

Fingerprint

Dive into the research topics of 'Fading unscented–extended kalman filter for multiple targets tracking with symmetric equations of nonlinear measurements'. Together they form a unique fingerprint.

Cite this